# Trustabl **Category:** ๐Ÿ’ป Developer Tools **Repository:** https://github.com/trustabl/agent-reliability-analyzer **Views:** 0 **Installs:** 0 **Upvotes:** 0 **Directory Page:** https://allmcps.com/mcp/trustabl ## Description Find and fix reliability and safety gaps in agent code, across nine agent SDKs. ## Claude Desktop Quick Installation Heuristic fallback โ€” verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low): ```json "mcpServers": { "trustabl": { "command": "npx", "args": ["-y","trustabl"] } } ``` ## Documentation & README

Trustabl โ€” open source AI agent reliability

Find and automatically fix guardrail gaps, unsafe tools, missing validation, and unbounded loops in Claude Agent SDK, OpenAI Agents SDK, Google ADK, LangChain, CrewAI, and MCP agents โ€” before production.

License: Apache-2.0 Latest release Total downloads Tests Go version
Detection rule count 9 SDKs supported 7 languages supported 5 detection scopes Analyzed surfaces Output formats

# Trustabl โ€” find and fix AI agent reliability gaps **Find what will make your AI agent fail โ€” then fix it with one command.** Trustabl scans an agent repository for the gaps that break agents in production: tool descriptions too vague for a model to know when to use them, missing retry and timeout handling, untyped parameters, absent guardrails, and tool grants that exceed what the agent claims to do. Then it applies the fix directly to your source. Every other agent scanner hands you a report. Trustabl hands you a patch. Reliability is engineered before deployment, not observed after it. **Scanning runs entirely on your machine.** No cloud scanner, no account, no code upload, no LLM โ€” deterministic static analysis. ```bash docker run --rm -v "$PWD:/repo" ghcr.io/trustabl/trustabl:latest scan /repo # try it, nothing installed brew install trustabl/tap/trustabl # macOS / Linux scoop bucket add trustabl https://github.com/trustabl/scoop-bucket # Windows scoop install trustabl trustabl scan . # find issues (fully local) trustabl scan . --format json > scan.json trustabl enrich --input scan.json --repo . --diff --apply # preview, then fix ``` 9 SDKs ยท 7 languages ยท human, JSON, or SARIF 2.1.0 output ยท CI-friendly exit codes ยท also runs as a local stdio MCP server (`trustabl mcp`). Deepest coverage for **Claude Agent SDK**, **OpenAI Agents SDK**, **Google ADK**, and **MCP servers**. Also scans LangChain / LangGraph, CrewAI, AutoGen / AG2, Pydantic AI, and the Vercel AI SDK โ€” see [COVERAGE.md](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/COVERAGE.md) for the full matrix. Scanning needs no key and no network. Applying fixes uses your own Anthropic, OpenAI, or Google key. ## What a scan looks like Real output, scanning an agent repo that ships a Claude Agent SDK client, an MCP server, a subagent, and two skills: ```console $ trustabl scan . Scan summary Languages: typescript, javascript SDKs: claude_agent_sdk Tool definitions: 2 (custom tools with function bodies) Agent tool grants: 14 (tool names the agent may call) MCP servers: 1 (createSdkMcpServer) Subagents: 1 (inbox-searcher) Skills: 2 (action-creator, listener-creator) Findings: 14 Overall score: 66% Surface readiness skill:action-creator 45% (5 findings) skill:listener-creator 54% (4 findings) agent:AIClient.queryStream 64% (2 findings) subagent:inbox-searcher 79% (1 finding) tool:search_inbox 98% (1 finding) tool:read_emails 100% (0 findings) Findings inbox-searcher [CSDK-201] HIGH Subagent is granted Bash (agent/.claude/agents/inbox-searcher.md:1-5) A subagent with shell access can run arbitrary commands if it is compromised or misdirected. fix: Remove `Bash` from the subagent's `tools:` list unless shell access is essential. Prefer specific tools (Read, Grep, Glob) for read-only roles. ``` Three things worth noticing: - **It scores each surface separately.** A repo-wide number hides the problem; `skill:action-creator` at 45% tells you where to look first. - **Every finding carries a fix**, not just a complaint โ€” and `trustabl enrich --apply` writes those fixes to source. - **The exit code is the CI gate.** `0` when nothing reaches medium severity, `1` when something does, so a pipeline can stop a bad agent from shipping. ## AI agents pass their demo and fail in production The failures are rarely exotic. They are the same handful of gaps, over and over: - An agent holding shell tools with **no input guardrails** - A tool making an HTTP call with **no timeout**, hanging the whole run - **Untyped tool parameters**, so the model guesses and guesses wrong - A tool description so vague the model calls the wrong tool โ€” 56% of MCP tool descriptions fail to state their purpose clearly, and 97.1% carry at least one description defect (Hasan et al., *MCP Tool Descriptions Are Smelly!*, [arXiv 2602.14878](https://arxiv.org/abs/2602.14878) โ€” 856 tools across 103 servers) - A **subagent granted `Bash`** despite a read-only description - A **skill that auto-approves unrestricted shell access** - **No retry handling**, so one transient 500 fails the task - An agent loop with **no iteration bound**, burning tokens until it is killed - A **user-controlled URL** flowing into a fetch โ€” SSRF, from your agent Every one of these is visible in the source before the agent ever runs. Trustabl finds them in seconds, offline, with no LLM โ€” and fixes them. The rest of this document explains *what Trustabl reasons about* and *how the scan works*, then covers building and running it. For the full implementation reference see [ARCHITECTURE.md](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/ARCHITECTURE.md); for the at-a-glance SDK coverage matrix see [COVERAGE.md](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/COVERAGE.md). ## What it analyzes โ€” the five-scope model Trustabl does not treat a repository as one undifferentiated blob. Every rule is classified into exactly one of five scopes, and each scope receives a different typed input: - **`tool`** โ€” fires once per tool definition. Input: a `ToolDef` (a `@function_tool` / `@tool` / `@claude_tool` function, a Claude TS `tool(name, description, schema, handler)` factory call, a `FunctionTool(fn)` ADK wrapper, an `@server.tool` MCP registration, or a bare shell-invoking function) plus its parsed file. Catches a missing docstring, an HTTP call with no timeout, untyped parameters, or an unnormalized path flowing into `open()`. (Hosted tools like `WebSearchTool()` are agent-scope edge data, captured as `HostedToolDef`, not `ToolDef`.) - **`agent`** โ€” fires once per agent declaration. Input: an `AgentDef` โ€” a Python `Agent(...)` / `SandboxAgent(...)` / `AgentDefinition(...)` call, a Claude TS typed-const `AgentDefinition`, a Claude TS sub-agent inline in `options.agents`, or the Claude TS `query(...)` main-thread agent (`QueryMainAgent`) โ€” with every constructor kwarg captured and its edges to tools, handoffs, and guardrails resolved. Catches an agent with shell tools and no `input_guardrails`, `tool_use_behavior="stop_on_first_tool"` paired with filesystem-touching tools, or a main-thread agent with unrestricted `allowedTools`. - **`subagent`** โ€” fires once per Claude Code subagent markdown declaration. Discovery is **hybrid**: canonical `.claude/agents/*.md` (any path depth, monorepo-safe) PLUS a frontmatter-shape fallback over all markdown files (gated on `name` + `tools`/`model`) that catches flat-collection repos which ship subagents under `categories/*.md`, `plugins//agents/*.md`, or similar layouts. Input: a `SubagentDef` parsed from frontmatter โ€” `name`, `description`, `tools[]` (verbatim) + `ToolGrants[]` (parsed permission grammar), `disallowedTools`, `model`, `permissionMode` (incl. `bypassPermissions`), `mcpServers`, `skills`, `isolation`, `hasHooks`. Catches a subagent granted the built-in `Bash` tool despite a read-only description (CSDK-110). Subagent presence alone contributes `claude_agent_sdk` to `SDKsDetected`, so the Claude pack loads and CSDK-110 fires on pure-markdown subagent collections. - **`skill`** โ€” fires once per Claude Code skill (`SKILL.md`, any path depth). Input: a `SkillDef` parsed from frontmatter โ€” `name`, `description`, `allowed-tools` โ†’ `ToolGrants[]`, `disable-model-invocation` โ€” plus body facts (dynamic-context exec commands, external URLs, prompt-injection markers) and a bundled-file inventory. Catches a skill that auto-approves unrestricted `Bash` (CSKILL-001), runs a dynamic-context command that performs network egress or reads secrets before the model sees it (CSKILL-003), or is model-invocable while granting side-effecting tools (CSKILL-050). Skills are markdown, so skill rules carry no `language:`; the `claude_skill` pack loads whenever a `SKILL.md` is present. - **`repo`** โ€” fires once per scan against the whole inventory. Catches project-wide gaps such as the OpenAI Agents SDK being present with no custom trace processor configured. ### The agent is the unit of analysis, not the repo A repo can declare zero, one, or many agents, across one or more SDKs. **Two agents in the same repo can be in completely different security postures** โ€” one wired with input/output guardrails, the other not. Agent-scoped findings therefore attribute to a *specific* agent at its constructor call site; flattening them to a single repo-level verdict would lose that attribution and be wrong. Discovery builds a small per-repo graph (tools, agents, subagents, and the edges between them) so agent-scope and subagent-scope rules can query it. ### Rules are scoped to one SDK *and* one language A Claude-SDK rule and an OpenAI-Agents-SDK rule that detect the same conceptual problem (a missing timeout, say) are two separate rules with SDK-specific explanation and fix text โ€” there is no cross-SDK casting. When a repo declares agents from multiple SDKs side by side, each agent is checked only against the rules for the SDK that declared it. The same holds across languages: a `language: python` rule will not fire on a TypeScript agent. ## How it reasons โ€” the scanning pipeline trustabl scans in four steps. Each step's output is the typed input to the next, with no shared state between runs โ€” and the inventory the early steps build is what makes policy selection *data-driven* rather than statically configured. The binary ships with **no embedded rules**. Before the pipeline runs, Trustabl resolves its detection rules from a separate git repository ([`agent-reliability-rules`](https://github.com/trustabl/agent-reliability-rules)) โ€” fetching the latest, caching the clone locally, and falling back to the cache when the network is unreachable. This decouples rule updates from binary releases: rules can be added or changed without rebuilding the scanner. The resolved rules commit is recorded in the result and folded into the `ScanID`, so a scan is honest about *which* rules produced it. If no rules can be fetched and none are cached, the scan exits `2` and tells you to run `trustabl rules pull` โ€” Trustabl never runs rule-less. ```mermaid flowchart LR target[("Agent repo
(local path or GitHub URL)")] recon["Recon
files ยท SDK deps"] inv["Inventory
Python + TS AST:
tools ยท agents ยท
subagents ยท MCP servers"] pol["Policy selection
load rules per
detected SDK ยท
META findings"] ana["Analysis
tool ยท agent ยท subagent ยท
repo detectors"] score["Scoring
per-surface score ยท
overall readiness"] out[("ScanResult
findings ยท scores
(human / JSON / SARIF)")] target --> recon --> inv --> pol --> ana --> score --> out ``` 1. **Recon** โ€” walk the repo and answer "what's in here" cheaply, without parsing any source language: languages present (by extension), SDK dependencies declared in manifests (`pyproject.toml` / `requirements.txt` / `Pipfile` / `poetry.lock` / `package.json` for the `claude-agent-sdk` / `@anthropic-ai/claude-agent-sdk` / `openai-agents` / `@openai/agents` / `google-adk` / `@google/adk` needles), the file inventory, and discovered agent components (MCP configs, hook scripts, `CLAUDE.md` and `AGENTS.md` guidance docs, `.claude/agents/*.md` subagents at any depth, `SKILL.md` skills, slash commands at both `.claude/commands/*.md` and `/commands/*.md`, `.claude-plugin/{plugin,marketplace}.json` manifests, sandbox policies). No tree-sitter parses happen here โ€” this step decides whether the expensive AST work is even worth attempting. 2. **Inventory** โ€” for each language Recon cleared, do the AST work and extract a typed inventory: `ToolDef`s with their config and body facts, `AgentDef`s with all kwargs captured, `SubagentDef`s / `SkillDef`s / `SlashCommandDef`s / `PluginManifest`s parsed from markdown and JSON frontmatter, `MCPServerDef`s, guardrails, sessions, and the resolved edges between agents and the tools/guardrails they reference. Detectors read fields off these structs โ€” they never re-parse raw source. 3. **Policy selection** โ€” load **only** the rule packs for SDKs actually *observed in code*. An SDK seen in code with no shipped pack emits a `META-001` info finding ("Trustabl does not currently audit this SDK") โ€” silence on an unknown SDK is wrong. A dep declared but never used in code emits a different info finding flagging the drift. 4. **Analysis** โ€” run the selected scope-aware detectors against the inventory. Findings carry the scope they fired at and attribute to the right location: tool file/line, agent call site, subagent markdown file, or the manifest. Three properties fall out of this staging, by design: - **Performance.** A repo with no Python skips Python AST work; a repo with only Claude TS code skips Python AST work AND OpenAI policy loading. - **Honest coverage.** An "unaudited SDK" info finding is louder than a zero-findings clean bill of health on an SDK Trustabl doesn't know. A `META-004` finding further distinguishes "audited and clean" from "could not audit โ€” discovery extracted nothing a rule targets." - **Determinism is a contract.** Same inputs โ†’ same `ScanID`, and the report is byte-stable across runs (findings sorted by `(RuleID, FilePath, Line)`, inventory slices sorted deterministically). CI consumers can diff scans without spurious churn. See [ARCHITECTURE.md ยง 2](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/ARCHITECTURE.md#2-pipeline) for the full diagram with typed inputs at each step. ### What's wired today Tool/agent AST discovery is wired for: - **Python** โ€” Claude Agent SDK (decorators), OpenAI Agents SDK, Google ADK, LangChain / LangGraph, CrewAI, AutoGen / AG2, and Pydantic AI. Discovery extracts tool definitions, agent constructors, hosted tools, MCP servers, guardrails, sessions. The bare `Agent(...)` constructor shared by OpenAI / ADK / CrewAI / Pydantic AI is import-gated per SDK so the classes never cross-match, and the shared `@tool` decorator is routed to the owning SDK by its import binding. - **TypeScript** โ€” Claude Agent SDK (the `tool()` factory, the `query()` main-thread `QueryMainAgent`, inline-in-`query()` sub-agents, typed-const `AgentDefinition`s, `createSdkMcpServer` and the four `options.mcpServers` config literals), OpenAI Agents SDK (the `tool({...})` factory, `new Agent({...})` and `Agent.create({...})`, 9 hosted-tool factories, MCP server classes across 3 transports plus the `MCPServers` wrapper, 4 `defineX` guardrail factories, and the `MemorySession` / `OpenAIConversationsSession` / `OpenAIResponsesCompactionSession` session classes โ€” gated on imports from `@openai/agents`, `@openai/agents-core`, or `@openai/agents-openai`), and Google ADK (the `new FunctionTool({...})` constructor, 5 agent constructors โ€” `new LlmAgent({...})` / `SequentialAgent` / `ParallelAgent` / `LoopAgent` / `RoutedAgent` โ€” 13 hosted-tool classes, and `subAgents` edges โ€” gated on imports from `@google/adk`), LangChain / LangGraph (the `tool(fn, {...})` factory, `DynamicStructuredTool` / `DynamicTool`, and `createReactAgent` / `createAgent` / `new AgentExecutor` โ€” gated on the `@langchain/*` / `langchain` / `langgraph` ecosystem), and the Vercel AI SDK (the `tool({...})` / `dynamicTool({...})` single-object factory, the call-based `generateText` / `streamText` / `generateObject` / `streamObject` agents and the class `ToolLoopAgent` / `Experimental_Agent`, with `tools` walked as an object/record, plus the `.tools.*()` hosted tools โ€” gated on the bare `ai` import). Handles `.ts` / `.tsx` / `.mts` / `.cts` plus JavaScript `.js` / `.jsx` / `.mjs` / `.cjs` with the `tree-sitter-typescript` and `tree-sitter-tsx` grammars (JavaScript routes to the tsx grammar โ€” a JS superset โ€” and is audited by the same `language: typescript` rule packs). TypeScript rule packs ship for the Claude Agent SDK (CSDK-010/011/012/013/014/016 tool rules; CSDK-120/130/131 agent rules), OpenAI Agents SDK (OAI-016/017/019/022/024 tool rules; OAI-105/116 agent rules), Google ADK (ADK-013/015/016 tool rules; ADK-109 agent rule), MCP (MCP-011/012/013/014 tool rules), LangChain (LC-010/011/012/013/014 tool rules; LC-111 agent rule), and the Vercel AI SDK (VAI-001..008 tool/agent rules; VAI-012 repo rule). A TS repo for any of these no longer produces a blanket `META-004`; see `COVERAGE.md` for the full matrix. JavaScript (`.js` / `.jsx` / `.mjs` / `.cjs`) is AST-parsed through the shared TypeScript-family pipeline: its tools and agents are discovered, tagged `javascript`, and audited by the `language: typescript` rule packs (both ES `import` and CommonJS `require()` bindings are recognized). Go has tree-sitter-go discovery for MCP tools (mark3labs/mcp-go and the official modelcontextprotocol/go-sdk), audited by the `language: go` rules in the MCP pack. C# has tree-sitter-c-sharp discovery for the official ModelContextProtocol SDK's `[McpServerTool]` methods, audited by the `language: csharp` rules. PHP has tree-sitter-php discovery for `#[McpTool]`-attributed methods (official mcp/sdk and community php-mcp/server), audited by the `language: php` rules. Rust has tree-sitter-rust discovery for the official rmcp crate's `#[tool]`-attributed methods (descriptions read from the `description = "..."` arg or the `///` doc comment), audited by the `language: rust` rules; other Go, .NET, PHP, and Rust SDKs are recognized as files by Recon but not yet AST-parsed. The rule schema's `language:` field gates per-language rule sets. ### Scope boundaries - **LLM enrichment is a separate post-scan step (`trustabl enrich`).** Rule-based detection (`trustabl scan`) makes no network call โ€” there is no LLM involved in the scan itself. `trustabl enrich` reads the scan output and calls the configured LLM provider (Anthropic, OpenAI, or Google Gemini) with BYOK (key stored via `trustabl llm key set` at `~/.config/trustabl/keys.json`, mode 0600). Each call carries a request timeout, and `--apply` rewrites a file only when its current contents still match what the model reviewed (writing a `.trustabl.bak` backup first) โ€” a stale scan is skipped, never mis-applied. With `--langsmith` (opt-in, requires `LANGSMITH_API_KEY`), tool-scope findings are additionally grounded in runtime trace evidence sampled from a LangSmith project: error rate, latency, and recent error messages for each flagged tool, carried on the output as `trace_evidence` and fed to the LLM alongside the static code snippet; tools with no trace history degrade per finding to plain static enrichment. - **Confidence scores are heuristic**, not LLM-judged, and not yet calibrated against a labelled real-agent corpus โ€” treat findings as signal to investigate. - **The CLI is the surface.** No web app, API server, or hosted service: pipe `--format json` or `--format sarif` into your own automation. On GitHub Actions, [`trustabl/trustabl-action`](https://github.com/trustabl/trustabl-action) wraps the scan and uploads SARIF to the Security tab for you; for any other CI, `--format sarif --output ` produces a SARIF 2.1.0 report that feeds `github/codeql-action/upload-sarif` or any SARIF-aware step. - **Trustabl is open core.** Everything documented here is Apache-2.0 and complete for its job: the scan needs no key and no network, and autofix uses your own LLM key. Policy generation, compliance mapping and signed governance snapshots are Trustabl Console, a separate commercial product. See [docs/open-source-vs-console.md](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/docs/open-source-vs-console.md) for the full capability split. ## What it produces Trustabl is a detect-and-report tool: it does **not** write or modify any files in the scanned repo. Each run produces a `ScanResult` containing: - **Findings** โ€” one per rule hit, each with `severity`, `confidence`, an `explanation`, a `suggested_fix`, and the location it fired at (tool file/line, agent call site, subagent file, or the manifest). A finding in a test-path file carries `"origin": "test"` and is excluded from scoring and the exit code by default โ€” see "Test-path findings" below. - **Per-surface readiness scores** (one per discovered tool, agent, subagent, or the repo as a whole) and an **overall score** (a breadth-aware, badness-weighted mean โ€” weak surfaces pull it down harder, but a single poor surface does not zero it; the score is a triage signal, not the CI gate). - **The discovered inventory** โ€” tools, agents, hosted tools, MCP servers, subagents, skills, slash commands, plugin manifests, and Claude settings โ€” surfaced at the top level for CI consumers. ### The summary's tool surface, broken out The human format honestly separates the three things people commonly conflate: ``` Tool definitions: 2 (custom tools with function bodies โ€” scored below) Agent tool grants: 14 (tool names the agent may call โ€” audited by agent-scope rules) Hosted tools: 1 (...) ``` Only the "Tool definitions" category flows through tool-scope rules (they have function bodies a rule can read). Agent grants and hosted instances are inputs to *agent-scope* rules, not unanalyzed โ€” they just don't appear in the per-surface readiness table. ### Output modes `--format human` (default) renders a human summary to stdout and live progress to stderr โ€” an animated spinner and progress bar on an interactive terminal, or plain `[phase] summary` lines when piped (CI-friendly). `--format json` marshals the full `ScanResult` for piping into your own automation. `--format sarif` emits a SARIF 2.1.0 document, suitable for `github/codeql-action/upload-sarif` and other SARIF-aware tools. The suggested fix is carried at the rule level (`help.text`); Trustabl emits no per-result `fixes[]`, so the document passes GitHub Code Scanning's schema validator (which rejects a `fix` that lacks `artifactChanges`). `--json-out ` and `--sarif-out ` write the JSON / SARIF document to a file independent of `--format` โ€” one scan can print the human summary to stdout while persisting both machine artifacts. The file bytes are identical to the matching `--format` stdout output. `--bom-out ` additionally writes a byte-stable CycloneDX 1.5 BOM of the dependencies the repo declares across every supported language โ€” `requirements.txt` / `pyproject.toml` / `Pipfile` (pip), `package.json` (npm), `go.mod` (Go), `composer.json` (Composer), `*.csproj` (NuGet), `Cargo.toml` (Cargo). It is pure inventory of DECLARED direct deps and makes no network call. Where the manifest carries a `license` field (`package.json`, `Cargo.toml`, `composer.json`, `pyproject.toml`), the SPDX identifier is included in each component's `licenses[]` array in the BOM. `--vuln-scan` turns that BOM into a vulnerability verdict: it matches the repo's concretely-pinned dependencies against a pinned [OSV](https://osv.dev) snapshot and reports each affected package as a finding carrying the advisory ID (CVE / GHSA / PYSEC / โ€ฆ), a CVSS-derived severity, and the first fixed version โ€” so a vulnerable dependency fails the scan through the normal severity gate and exit codes and lands in the JSON / SARIF output alongside the rule findings, on `ScanResult.vulnerabilities`. Unlike the rest of a scan it is **opt-in and online**: the OSV snapshot is fetched from osv.dev on first use, cached under your user cache directory, and then **cache-first** โ€” a later `--vuln-scan` reuses the cached database (no re-download) until it is older than 24h, so repeated scans are fast and offline-capable. `trustabl vulndb pull` refreshes the cache on demand; `--no-rules-update` pins to the cache at any age (fully offline). Only concretely-pinned versions are matched โ€” a declared range (`^1.0`, `>=2`) can't be resolved to one version without a lockfile, so it is left unmatched rather than guessed. The snapshot version is folded into the `ScanID` only when `--vuln-scan` is on, so the result is honest about which vulnerability data produced it while a default scan stays byte-identical to before. Combining `--vuln-scan` with `--bom-out` upgrades the CycloneDX document from a plain inventory into a BOM **plus VEX**: the matched advisories are emitted as a CycloneDX 1.5 `vulnerabilities[]` array โ€” each with the advisory ID, an OSV `source`, a severity `rating`, an upgrade `recommendation`, and an `affects[]` reference linking it to the affected component's `bom-ref` โ€” so a single `trustabl scan ./repo --vuln-scan --bom-out bom.json` produces a standards-based artifact that any CycloneDX-aware tool can ingest. Without `--vuln-scan` the `vulnerabilities[]` array is omitted and the BOM stays pure inventory. `--format json` and `--format sarif` are progress-silent and byte-stable across identical-input runs (pure functions of the `ScanResult`). The human format is not byte-stable by design: its ANSI color is auto-detected from the terminal (TTY vs pipe, `NO_COLOR`), so the same scan can render with or without color. Use `--no-color`, or diff the JSON/SARIF output, when byte-stability matters. ### Test-path findings A finding whose file lives under a test path (`tests/`, `__tests__/`, `testdata/`, `test_*.py`, `*_test.go`, `*.spec.ts`, โ€ฆ) is still reported in every format โ€” nothing is silently hidden โ€” but by default it is **excluded from the readiness score and does not fail the build**: a `WebSearchTool` declared in `tests/test_adapter.py` is not the same finding as one shipped in a production agent, and scoring them identically made the report non-actionable. Each such finding carries `"origin": "test"` in JSON, an `origin` property plus a `result.suppressions` entry in SARIF (excluded from GitHub code scanning's default alert view, still present in the raw log), and renders under a trailing "Test-path findings (not scored)" section in the human output instead of mixing into the scored groups above it. Pass `--include-test-paths` to score and fail on these findings exactly like any other โ€” useful if your project ships code that legitimately lives under a `tests/`-shaped path. ### Diagnostics (`--verbose` / `--debug`) `--verbose` (`-v`) narrates the scan on **stderr**: rule provenance (repo, ref, resolved SHA, and any cache fallback), per-phase discovery counts (languages, tools, agents, detected SDKs, loaded detectors, unaudited SDKs), output destinations, and a final result summary (scan ID, score, findings by severity, exit code). `--debug` adds everything `--verbose` shows plus per-phase timing and capped per-entity / per-finding detail (each discovered tool/agent and each finding with its `file:line`). Both are **global** flags โ€” they work on `scan`, `mcp`, and `rules pull`, and may appear before or after the subcommand (`trustabl -v scan โ€ฆ` or `trustabl scan -v โ€ฆ`). `--debug` implies `--verbose`. Both write **only to stderr**, so they never perturb the report on stdout or the JSON/SARIF byte-stability contract: `--format json --debug` still emits a clean document on stdout while the diagnostics stream to stderr. Diagnostic color follows the same rules as the report (off under `--no-color`, `NO_COLOR`, or when stderr is not a terminal). Because an animated progress panel and interleaved log lines would corrupt each other on the same stderr, `--verbose`/`--debug` automatically render progress as plain `[phase]` lines instead of the live spinner. **Saving diagnostics to a file.** There is no dedicated `--log-file` flag โ€” because diagnostics are a separate stream (stderr), redirecting stderr is the intended mechanism: ```bash # Report and diagnostics to separate files (stdout vs stderr) trustabl scan ./repo --debug --format json >report.json 2>diagnostics.log # Human report on screen, diagnostics to a file trustabl scan ./repo --debug 2>diagnostics.log # Everything (report + diagnostics) in one file trustabl scan ./repo --debug &>everything.log ``` With `--format json`/`sarif` progress is off, so the stderr file is diagnostics-only; with `--format human` it also carries the plain `[phase]` progress lines. Exit codes (a test-path finding is excluded from this gate unless `--include-test-paths` is set โ€” see "Test-path findings" above): - `0` โ€” no findings โ‰ฅ medium severity (or no findings at all). - `1` โ€” at least one finding โ‰ฅ medium severity, OR `--strict` with any finding present. - `2` โ€” scanner / I/O error, OR no usable rules found and none fetchable (run `trustabl rules pull`), OR a signed channel (`--rules-source`) that failed verification (bad signature, untrusted/expired key, channel confusion, an expired or rolled-back statement, or a digest mismatch) โ€” Trustabl refuses to run unverified rules. OpenShell surfaces are still discovered (shell-invocation functions, `openshell/*.yaml` policies) and reported on a `Risk surfaces: openshell` block in the human format: the count of shell-invoking functions, the first three file:line locations (deterministically sorted), a `why:` line stating the threat model (a prompt-injected agent that exposes one of these as a callable tool can run arbitrary commands), and a `fix:` line with concrete remediations (sandbox, allowlist, drop `shell=True`, keep shell logic out of agent-callable code). The OSH-* detection rules that audited these surfaces have moved to a closed-source companion project; with no OSH rules shipped, such repos fire no rule and no `META` finding โ€” the block makes the unaudited risk legible without claiming an audit happened. OpenShell is a risk surface, not an SDK, so it is not flagged as "unaudited" the way an unknown SDK would be. ## Install ### Homebrew (macOS, Linux) ```sh brew install trustabl/tap/trustabl ``` ### Scoop (Windows) ```sh scoop bucket add trustabl https://github.com/trustabl/scoop-bucket scoop install trustabl ``` ### Docker ```sh docker run --rm -v "$PWD:/repo" ghcr.io/trustabl/trustabl:latest scan /repo ``` ### Direct download Grab a prebuilt archive for your platform from the [Releases page](https://github.com/trustabl/agent-reliability-analyzer/releases). Each release includes a `checksums.txt` and a build-provenance attestation; verify with: ```sh gh attestation verify --repo trustabl/agent-reliability-analyzer ``` > Archives released **before** the repository was renamed verify only under the > old slug (`--repo trustabl/trustabl`): the Sigstore certificate binds the > repository path as it was at signing time, so the recorded identity cannot > follow a rename. ## Attestation ### Test Usage Example #### **Prerequisite and setup:** Install cosign (any **2.x or 3.x** โ€” Trustabl adapts to the installed version) ##### Add to target folder path: `export PATH=":$PATH"` ##### Export and Generate Key Pair: `export COSIGN_PASSWORD="" ` skip the passphrase prompt (omit for a real key) `cosign generate-key-pair` writes cosign.key (private) + cosign.pub (public) ##### Trustabl Scan and Attest: `./trustabl.exe scan https://github.com/google/adk-samples --json-out report.json --attest --attest-key cosign.key --attest-bundle att.bundle.json --attest-no-tlog` ##### VERIFICATION `./trustabl.exe verify report.json --key cosign.pub --bundle att.bundle.json --no-tlog` #### Keyless (CI / no key to manage) Keyless signs with your ambient **OIDC identity** instead of a key pair โ€” nothing to generate or store. In CI (GitHub Actions) the runner's identity is used automatically; **on a laptop it opens a browser to log in**. Either way the signing event is recorded in the **public Rekor transparency log** โ€” so use key mode above if that visibility is unacceptable. No `--no-tlog` here (keyless *is* the transparency-log path), so the cosign v2/v3 difference does not apply. ##### Scan and Attest (keyless): `./trustabl.exe scan https://github.com/google/adk-python --json-out report.json --attest --attest-bundle att.bundle.json` ##### VERIFICATION (keyless โ€” you must pin who signed and the issuer): `./trustabl.exe verify report.json --bundle att.bundle.json --certificate-identity "" --certificate-oidc-issuer "https://token.actions.githubusercontent.com"` In GitHub Actions the identity is the workflow ref, e.g. `https://github.com/OWNER/REPO/.github/workflows/scan.yml@refs/heads/main`. ### cosign (optional โ€” only for scan attestation) Trustabl's `attest` / `verify` commands and `scan --attest` shell out to the [cosign](https://docs.sigstore.dev/cosign/system_config/installation/) CLI โ€” cosign does the signing and verification, and Trustabl ships no keys of its own. It is needed **only** if you use attestation; a plain `scan` never touches it. ```sh # macOS / Linux brew install cosign # Windows scoop install cosign ``` In CI you do not install it by hand โ€” the Trustabl GitHub Action and GitLab component add `sigstore/cosign-installer` for you. #### Scan with attestation โ€” step by step (key mode, offline) Key mode signs with a local key pair and skips the public transparency log โ€” no browser, no network, ideal for a laptop or air-gapped run. > **cosign version:** works with cosign **2.x and 3.x** โ€” Trustabl selects the > right no-transparency-log mechanism per version automatically > (`--tlog-upload=false` on v2; a no-Rekor `--signing-config` on v3+, which > removed that flag). On a PATH install the command is `trustabl`; for a local > Windows build it is `.\trustabl.exe`. > **Attestation tiers:** this is the **free-tier basic attestation** โ€” it signs > scan *provenance* (scan ID, rules version, reliability score, verdict, severity > counts). Behavioral and policy-aware attestations are on the paid roadmap. **Step 0 โ€” install cosign** (see the commands above for your OS). **Step 1 โ€” generate a signing key pair:** ```sh export COSIGN_PASSWORD="" # skip the passphrase prompt (omit for a real key) cosign generate-key-pair # writes cosign.key (private) + cosign.pub (public) ``` **Step 2 โ€” scan and sign in one step:** ```sh trustabl scan https://github.com/google/adk-samples \ --json-out report.json \ --attest --attest-key cosign.key --attest-bundle att.bundle.json --attest-no-tlog ``` Writes `report.json` (the scan result), `trustabl-predicate.json`, and the signed `att.bundle.json`. Exit 1 only means findings were present โ€” the bundle is still written (it signs the verdict, pass or fail). **Step 3 โ€” verify (consumer side):** ```sh trustabl verify report.json --key cosign.pub --bundle att.bundle.json --no-tlog ``` `Verified OK`, exit 0 โ€” the report is authentic and unmodified. **Step 4 โ€” (optional) prove tamper detection:** ```sh echo '{"tampered":true}' >> report.json trustabl verify report.json --key cosign.pub --bundle att.bundle.json --no-tlog ``` Verification now FAILS (exit 1): the signature is bound to the exact report bytes, so any edit is caught. Keyless signing (no private key to manage) is the default in CI, where an ambient OIDC identity exists; it also records the signature in the public Rekor transparency log. See [Use](#use) for the full command surface. ### Claude Code plugin The plugin installs two skills (`trustabl-scan` and `trustabl-enrich`), a `SessionStart` hook, and a bundled MCP server โ€” and auto-downloads the pinned CLI binary on first session (no `sudo`, nothing outside Claude Code's plugin data directory touched). Install from within a Claude Code session using the `/plugin` slash command: ``` /plugin install trustabl@claude-plugins-official ``` Then reload to activate: ``` /reload-plugins ``` After installation, the `mcp__trustabl__scan` tool is available for direct calls, the `trustabl-scan` and `trustabl-enrich` skills appear in the skill picker, and the hook confirms the binary is ready at session start. Uninstall with `/plugin uninstall trustabl`. ### Claude Code agent A standalone subagent (`trustabl`) runs the full scan โ†’ enrich โ†’ review โ†’ apply pipeline interactively. It does not require the plugin โ€” just the `trustabl` binary already on your PATH. Copy the agent file into your project or home config: ```sh # Project-level (scoped to this repo) curl -fsSL https://raw.githubusercontent.com/trustabl/agent-reliability-analyzer/main/agents/trustabl.md \ -o .claude/agents/trustabl.md # Global (available in every project) curl -fsSL https://raw.githubusercontent.com/trustabl/agent-reliability-analyzer/main/agents/trustabl.md \ -o ~/.claude/agents/trustabl.md ``` Once installed, invoke it via `@trustabl` in Claude Code or select it from the subagent picker. It will ask which directory to scan, run `trustabl scan` and `trustabl enrich`, then walk you through each proposed fix as a diff. The enrich step requires an Anthropic API key. Set it before invoking the agent: ```sh export ANTHROPIC_API_KEY=sk-ant-api03-... # or: trustabl llm key set ``` ### From source Requires `CGO_ENABLED=1` because the AST parsers use tree-sitter (Python + TypeScript + TSX bindings), which is a C library: ```bash # macOS / Linux CGO_ENABLED=1 go build -o trustabl ./cmd/trustabl # Cross-compile: pick a C toolchain for the target. zig is the easiest. CGO_ENABLED=1 CC="zig cc -target x86_64-linux-gnu" \ GOOS=linux GOARCH=amd64 go build -o trustabl-linux ./cmd/trustabl ``` This is the cost of using tree-sitter for accurate AST parsing. If a single-binary, no-CGO distribution becomes a hard requirement later, the swap target is `github.com/go-python/gpython` for Python (with lower fidelity on modern Python); TypeScript would need a separate replacement. ## Use ```bash # Local repo trustabl scan ./path/to/agent-repo # GitHub repo (shallow clone to temp dir, removed on exit) trustabl scan https://github.com/org/repo # Restrict detectors trustabl scan ./repo --detectors claude_sdk trustabl scan ./repo --detectors openai_sdk trustabl scan ./repo --detectors google_adk trustabl scan ./repo --detectors claude_sdk,openai_sdk,google_adk # --detectors openshell is accepted but selects zero rules (pack is closed-source now) # Agent Skill security (SKILL.md) โ€” flags unrestricted allowed-tools (a bare # `Bash` grant), pre-model dynamic-context exec, bundled-script network egress / # secret reads, committed secrets, hidden-Unicode prompt injection, and a # description that claims read-only while granting side-effecting tools (the # CSKILL-* rules). Skills are discovered and scanned automatically. trustabl scan ./repo # scans skills alongside tools/agents/MCP trustabl scan ./repo --detectors claude_skill # only the Agent Skill (CSKILL-*) rules trustabl scan ./path/to/my-skill # point straight at one skill's directory # Dependency BOM (supply chain): export the repo's DECLARED deps across all # supported languages (pip / npm / Go / Composer / NuGet / Cargo manifests) as a # CycloneDX SBOM, to hand to OSV-Scanner / Dependabot / syft. Pure inventory โ€” # the scan itself does no CVE lookup. trustabl scan ./repo --bom-out sbom.json # Vulnerability scan (opt-in, online): match the repo's pinned deps against the # OSV database and FAIL on known CVEs โ€” advisory id, CVSS severity, fixed version. trustabl vulndb pull # pre-download OSV (optional; --vuln-scan auto-fetches) trustabl scan ./repo --vuln-scan # BOM inventory + CVE verdict in one pass trustabl scan ./repo --vuln-scan --bom-out bom.json # CycloneDX BOM + VEX (vulnerabilities[]) in one file # License scan (opt-in): flag dependencies with copyleft licenses (GPL-2.0, # GPL-3.0, AGPL-3.0, LGPL-2.1, SSPL-1.0) as medium-severity findings. # License data is read from the manifest at parse time โ€” no network call. trustabl scan ./repo --license-scan trustabl scan ./repo --license-scan --bom-out bom.json # findings + BOM with licenses[] # Secret scan (opt-in): walk all text files in the repo for hardcoded # credential literals (SECRET-LIT-001, high) and scripts that read # credential environment variables (SECRET-ENV-001, medium). trustabl scan ./repo --secret-scan # Test-path findings (a tests/ agent, test_*.py, *.spec.ts, โ€ฆ) are always # reported but excluded from scoring and the exit code by default โ€” see # "Test-path findings" below. --include-test-paths scores and fails on them # like any other finding. trustabl scan ./repo --include-test-paths # JSON output for CI piping trustabl scan ./repo --format json # SARIF output for GitHub Code Scanning / SARIF-aware tools trustabl scan ./repo --format sarif > trustabl.sarif # Write the report to a file instead of stdout (any format). --output writes # the file even when the scan exits 1 on findings, so a CI step can upload it. trustabl scan ./repo --format sarif --output trustabl.sarif # One scan, both machine artifacts written to files (human summary to stdout) trustabl scan ./repo --json-out trustabl.json --sarif-out trustabl.sarif # Exit 1 on any finding regardless of severity trustabl scan ./repo --strict # --- Attestation (opt-in; requires the cosign CLI on PATH) ------------------- # Sign the JSON report into a cosign attestation of the SCANNED repo's result. # Keyless by default: in CI it uses the runner's ambient OIDC identity (no keys # to manage) and logs the signing event to the PUBLIC Rekor transparency log. trustabl scan ./repo --json-out trustabl.json --attest trustabl attest trustabl.json # same, as a separate step # Offline / private signing with a key (no public transparency log): trustabl attest trustabl.json --key cosign.key --no-tlog # Verify (run where you CONSUME the attestation). Keyless pins who signed + issuer: trustabl verify trustabl.json \ --certificate-identity https://github.com/OWNER/REPO/.github/workflows/scan.yml@refs/heads/main \ --certificate-oidc-issuer https://token.actions.githubusercontent.com trustabl verify trustabl.json --key cosign.pub --no-tlog # key-mode, offline # Download / refresh the detection rule packs into the local cache trustabl rules pull # Validate a local rule-pack directory against this build's schema (CI gate # for the agent-reliability-rules repo โ€” strict-loads every pack, fails on the first error) trustabl rules validate ./trustabl-rules # Use a custom rules repo, or pin a specific released ruleset (env: TRUSTABL_RULES_REPO). # Default pulls the latest reviewed rules from agent-reliability-rules main; pin a tag for stability. trustabl scan ./repo --rules-repo https://github.com/org/my-rules trustabl scan ./repo --rules-ref v0.1.0 # Air-gapped / offline: skip the network fetch, use the cached rules only trustabl scan ./repo --no-rules-update # Progress output (human format): animated on a terminal, plain lines when piped trustabl scan ./repo # spinner + bars on a TTY; "[phase] summary" lines when piped trustabl scan ./repo --no-progress # disable progress entirely # Diagnostics on stderr (global flags; stdout/report unaffected) trustabl scan ./repo --verbose # -v: rule provenance, discovery counts, result summary trustabl scan ./repo --debug # + per-phase timing and per-entity/per-finding detail trustabl scan ./repo --debug --format json > out.json # clean JSON on stdout, diagnostics on stderr # Run as a stdio MCP server so an MCP client (Claude Code, Cursor, Claude # Desktop) can scan code an agent just wrote (see "Run as an MCP server" below) trustabl mcp # Configure LLM provider, then enrich a scan result with AI explanations and fixes export ANTHROPIC_API_KEY=sk-ant-api03-... # preferred: env var (works in CI, no setup) trustabl llm list # show configured providers with masked keys trustabl llm key set # prompt securely for an API key (persistent) trustabl llm key set sk-ant-api03-... # set key non-interactively trustabl llm key get # show masked key for active provider trustabl llm key delete # delete key with confirmation prompt trustabl llm model set claude-sonnet-4-6 # change model for active provider trustabl llm base-url set http://host:4000 # set API base URL (only meaningful for "custom") trustabl llm provider set openai # switch active provider (auto-creates entry) trustabl llm provider list # list configured providers # Self-hosted / local model server (any OpenAI-compatible endpoint, e.g. a # LiteLLM or vLLM gateway). Two ways to configure it: # # 1. Env vars โ€” no persistent config, works in CI: # OPENAI_BASE_URL alone activates "custom", ahead of a plain OPENAI_API_KEY. # No default model, so TRUSTABL_LLM_MODEL is required. OPENAI_API_KEY is # optional: only set it if the endpoint actually checks it. export OPENAI_BASE_URL=http://localhost:4000 export TRUSTABL_LLM_MODEL=qwen-32b # # 2. Persistent config โ€” same three fields, saved to ~/.config/trustabl/keys.json: trustabl llm provider set custom trustabl llm base-url set http://localhost:4000 trustabl llm model set qwen-32b # trustabl llm key set is optional โ€” skip it if the endpoint needs no key # Enrich a scan result (requires any configured LLM provider โ€” a custom # endpoint may not need a key, every other provider does) trustabl scan ./myrepo --format json | trustabl enrich --repo ./myrepo # pipe scan into enrich (stdout) trustabl enrich --input scan.json --repo ./myrepo --output enriched.json # file in, file out trustabl enrich --input scan.json --repo ./myrepo --diff # preview proposed fixes as a unified diff (stderr) trustabl enrich --input scan.json --repo ./myrepo --diff --apply # preview and apply fixes trustabl enrich --input scan.json --repo ./myrepo --apply # apply fixes without previewing trustabl enrich --input scan.json --repo ./myrepo --rule CSDK-010 # focus on one rule trustabl enrich --input scan.json --repo ./myrepo --only-enriched # CI: only enriched findings # Ground tool findings in LangSmith runtime traces (opt-in; error rates, latency, # recent errors are fetched per flagged tool and fed to the LLM as evidence) export LANGSMITH_API_KEY=lsv2_... # BYOK; LANGSMITH_ENDPOINT overrides for self-hosted trustabl enrich --input scan.json --repo ./myrepo --langsmith # project: $LANGSMITH_PROJECT or "default" trustabl enrich --input scan.json --repo ./myrepo --langsmith --langsmith-project prod ``` Rules are cached under your OS cache dir (`os.UserCacheDir()`, e.g. `%LocalAppData%\trustabl\rules\` on Windows, `~/.cache/trustabl/rules/` on Linux). The first scan (or an explicit `trustabl rules pull`) populates it; each subsequent scan checks for an update first (unless `--no-rules-update`), falling back to the cached rules if the fetch fails. **Signed rules channels (default).** A plain `trustabl scan` resolves rules from the signature-verified **production** release channel: Trustabl verifies a signed channel statement against an embedded trust keyring, fetches the bundle it commits to, and refuses (exit `2`) on any verification failure rather than running unverified rules. `--rules-source git` selects the unsigned git path explicitly, and `--rules-repo` / `--rules-ref` imply it; a non-default channel can still be pointed at a fork with `--rules-source --rules-repo ` to test a signed fork. (`--channel ` is a deprecated alias for `--rules-source `.) The **default scan now uses the signed production channel**; set `TRUSTABL_REQUIRE_SIGNED=1` (or `--require-signed`) to forbid the unsigned git fallback entirely in CI. Already-shipped pre-cutover binaries are unaffected (the default and keyring are compiled in); upgrading shifts `ScanID` once as the origin tag and git-SHA become the channel's bundle digest. A scan that did not use blessed production rules (a pre-release channel, or a custom `--rules-repo` source) is watermarked in the report and in the JSON `rules_origin` field, and its provenance is folded into `ScanID`. This build embeds the rule-signing public key, so a signed `--rules-source` runs the verification pipeline and refuses (exit `2`) only on a genuine verification failure (bad signature, untrusted or expired key, channel mismatch, expired or rolled-back statement, or digest mismatch). ### Pre-coding constraints (trustabl forge) `trustabl forge` is the counterpart to `trustabl scan`: instead of auditing code *after* it is written, it generates a combined pre-coding `SKILL.md` that tells an agent *before* it writes any code which patterns to avoid. The generated skill organizes rules by SDK and scope (tool, agent, subagent, repo, skill) and is ordered by severity so the highest-risk constraints appear first. **How SDK detection works.** Forge scans the target's dependency manifests โ€” `pyproject.toml`, `requirements.txt`, `Pipfile`, `poetry.lock`, `package.json`, and `go.mod` โ€” to determine which SDK policy packs to include. This is the same lightweight dep-file recon that `trustabl scan` performs in its recon step: no AST parsing, fast, and safe on any repo. When no manifests are found (or none declare a recognized SDK), forge exits `1` and tells you what to pass via `--policy`. ```bash # Auto-detect SDKs from the current directory trustabl forge # Auto-detect from a specific repo path trustabl forge /path/to/repo # Add a policy on top of auto-detected SDKs โ€” useful when introducing a new # SDK that is not yet in the dependency manifest trustabl forge --policy openai_sdk trustabl forge /path/to/repo --policy claude_sdk,mcp # Write the generated SKILL.md to a file instead of stdout trustabl forge -o .claude/skills/trustabl-pre-coding/SKILL.md # Pin a specific rules version (same as trustabl scan --rules-ref) trustabl forge --rules-ref v0.3.0 # Backward-compatible: generate only the Agent Skill (CSKILL-*) rules trustabl forge --policy claude_skill ``` **Available policy categories** (pass to `--policy`): | Category | SDK / framework | |---|---| | `claude_sdk` | Claude Agent SDK (Python + TypeScript) | | `openai_sdk` | OpenAI Agents SDK (Python + TypeScript) | | `google_adk` | Google Agent Development Kit (Python + TypeScript) | | `mcp` | Model Context Protocol servers | | `langchain` | LangChain / LangGraph (Python + TypeScript) | | `crewai` | CrewAI (Python) | | `pydantic_ai` | Pydantic AI (Python) | | `vercel_ai` | Vercel AI SDK (TypeScript) | | `autogen` | AutoGen / AG2 (Python) | | `claude_skill` | Claude Code skills (`SKILL.md`) | | `openshell` | Shell-invocation tools (no rules in the current pack) | Multiple categories are comma-separated: `--policy openai_sdk,mcp`. **What the output contains.** The generated file is a valid `SKILL.md` with: - A frontmatter block (`name: trustabl-pre-coding`, `allowed-tools: Read`, `disable-model-invocation: false`). - A passive stamp comment embedding the rules SHA, date, schema version, template (layout) version, and detected SDK list โ€” so you know exactly which ruleset and layout produced the file and when to regenerate. - A `## How to Apply These Constraints` apply-loop section, immediately after the stamp: a static four-step procedure telling the model to check each definition it writes against the matching constraints, name any violation by rule ID, apply that rule's directive, and log the repair. This is a self-check the model performs โ€” it does not run `trustabl scan` itself; scanning the resulting code remains a separate step. - One `## SDK Name` section per detected SDK, each containing `### Tool Rules`, `### Agent Rules`, `### Subagent Rules`, `### Repo Rules`, and `### Skill Rules` subsections (empty subsections are omitted). - Per-rule blocks: **Directive** (the fix, first sentence), **Why** (the explanation, first sentence), **When this applies**, severity, and confidence. Drop the output into `.claude/skills/trustabl-pre-coding/SKILL.md` in the agent repo and Claude Code will invoke it automatically before any agent code is written. Re-run `trustabl forge` after adding a new SDK dependency, after pulling a rules update, or after upgrading to a forge version with a newer template โ€” `trustabl forge check` reports staleness from either cause. ### Continuous integration Two CI patterns are supported, and they compose: - **Gate the build.** The exit code is the gate: `0` clean, `1` on a finding of medium severity or higher (`--strict` lowers the bar to any finding), `2` on an operational error. A bare `trustabl scan ./repo` in a job step fails the job when it should. - **Publish to GitHub Code Scanning.** On GitHub Actions, the [`trustabl/trustabl-action`](https://github.com/trustabl/trustabl-action) runs the scan and uploads the SARIF to the repository's Security tab in a single step (`upload-sarif` defaults to `true`), with inline PR alerts and optional threshold gating โ€” the recommended path, and the single source of truth for the workflow. Outside GitHub Actions, `--format sarif --output ` writes a SARIF 2.1.0 report that any `github/codeql-action/upload-sarif` or SARIF-aware step can publish. Because `--output` writes the file before the findings-based exit code is applied, the scan step can run with `continue-on-error: true` and the upload with `if: always()`, so a scan that finds issues still surfaces them instead of aborting the run with nothing uploaded. The SARIF document is a pure function of the scan result: byte-stable across identical-input runs, repo-relative file URIs, and a stable `partialFingerprints` per finding so Code Scanning deduplicates alerts across runs rather than re-opening them. ### Run as an MCP server `trustabl mcp` runs a Model Context Protocol (MCP) server over stdio, so an MCP client (Claude Code, Cursor, Claude Desktop) can scan a directory an agent just edited and read the findings back. It is the same scan as `trustabl scan`, exposed as an MCP tool โ€” it opens no network port. The server speaks JSON-RPC on stdout, so it writes nothing else there; status lines and diagnostics go to stderr. It exposes two tools: - `scan` โ€” input `{ "path": "", "rules_ref": ""?, "vuln_scan": true? }`. Scans `path` and returns the full scan result (findings, scores, discovered inventory) as JSON โ€” the same shape as `--format json`. Set `vuln_scan: true` to also match declared dependencies against a pinned OSV snapshot and report known CVEs (mirrors `--vuln-scan`; off by default). - `version` โ€” reports the build version, commit, and date. Register it with an MCP client by pointing the client at the binary with the `mcp` argument over stdio. For Claude Code: ```bash claude mcp add trustabl -- trustabl mcp ``` For Gemini CLI, add to `~/.gemini/settings.json`: ```json { "mcpServers": { "trustabl": { "command": "trustabl", "args": ["mcp"] } } } ``` For OpenAI Codex, add to `~/.codex/config.toml`: ```toml [mcp_servers.trustabl] command = "trustabl" args = ["mcp"] ``` Or configure it directly in a client's MCP config (the `mcpServers` stdio shape used by Claude Desktop / Cursor): ```json { "mcpServers": { "trustabl": { "command": "trustabl", "args": ["mcp"] } } } ``` The rules-source flags (`--rules-repo`, `--rules-ref`, `--no-rules-update`) work on `trustabl mcp` exactly as on `trustabl scan`; a client may also pass a per-call `rules_ref` in the `scan` tool arguments, which overrides the command-level `--rules-ref` for that call. ### Claude Code plugin (self-audit at generation time) Trustabl ships a Claude Code plugin under [`.claude-plugin/`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/.claude-plugin/) with two skills that form a scan-and-fix loop: - **[`trustabl-scan`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/skills/trustabl-scan/)** โ€” triggers right after agent, tool, subagent, or MCP-server code is written or changed and calls Trustabl's `scan` tool (the bundled MCP server, `mcp__trustabl__scan`) to self-audit it before committing, upstream of CI. - **[`trustabl-enrich`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/skills/trustabl-enrich/)** โ€” takes the output of a `trustabl scan` run (JSON, SARIF, or pasted terminal text) and applies each finding as a targeted code edit, guided entirely by the scan's own `explanation` and `suggested_fix` fields. It does not re-run the scanner; use `trustabl-scan` first, then invoke `trustabl-enrich` with the results. Scanning runs through a **bundled MCP server**: [`.mcp.json`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/.mcp.json) registers a `trustabl` server whose command is a launcher ([`scripts/trustabl-mcp.sh`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/scripts/trustabl-mcp.sh)) exposing the `mcp__trustabl__scan` tool. The launcher and a `SessionStart` hook ([`hooks/hooks.json`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/hooks/hooks.json) โ†’ [`scripts/check-trustabl.sh`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/scripts/check-trustabl.sh)) share install logic ([`scripts/lib-trustabl.sh`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/scripts/lib-trustabl.sh)) that downloads the pinned CLI version from GitHub Releases, verifies it against the release `checksums.txt`, and installs it into the plugin's private data directory (`$CLAUDE_PLUGIN_DATA` โ€” no `sudo`, nothing outside that dir touched). The install is idempotent (re-runs only when the pin changes or the copy is missing/corrupt), and the launcher installs synchronously before starting the server, so there is no first-session race. The same binary is exposed as `$TRUSTABL_BIN` for the enrich skill's direct-CLI path. When auto-install cannot run (offline first session, an unsupported platform, or missing `curl`/`tar`) it falls back to whatever `trustabl` is on `PATH`; the system-wide install stays a consented step inside `trustabl-scan`. The plugin runs no network service of its own and modifies nothing outside the scan target. ### Gemini CLI extension (self-audit at generation time) Trustabl ships a Gemini CLI extension under [`gemini-extension.json`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/gemini-extension.json) with the same two skills available in the Claude Code plugin. **Prerequisites.** Install the Trustabl binary first โ€” the extension does not auto-install it the way the Claude Code plugin does (Gemini CLI has no private plugin data directory): ```bash # macOS / Linux brew install trustabl/tap/trustabl # Windows scoop bucket add trustabl https://github.com/trustabl/scoop-bucket scoop install trustabl ``` **Install the extension:** ```bash gemini extensions install https://github.com/trustabl/agent-reliability-analyzer ``` **Register the MCP server** so Gemini CLI can call `mcp__trustabl__scan`. Add to `~/.gemini/settings.json`: ```json { "mcpServers": { "trustabl": { "command": "trustabl", "args": ["mcp"] } } } ``` **How it works.** When a Gemini CLI session starts, the extension injects [`GEMINI.md`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/GEMINI.md) as context, which pulls in the full `trustabl-scan` and `trustabl-enrich` skill content via `@` imports. Gemini then treats those skills exactly as it would any loaded context: it runs the scan after you write or change agent, tool, or MCP-server code, and offers to apply findings via `trustabl-enrich`. The MCP tool is named `mcp__trustabl__scan` โ€” the same name as in Claude Code. **Update the extension later:** ```bash gemini extensions update trustabl ``` ### OpenAI Codex plugin (self-audit at generation time) Trustabl ships an OpenAI Codex plugin under [`.codex-plugin/`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/.codex-plugin/) with the same two skills. **Prerequisites.** Install the Trustabl binary first: ```bash # macOS / Linux brew install trustabl/tap/trustabl # Windows scoop bucket add trustabl https://github.com/trustabl/scoop-bucket scoop install trustabl ``` **Install the plugin.** In Codex CLI, open the plugin search interface and search for `trustabl`: ```bash /plugins ``` Search for `trustabl` and select **Install Plugin**. In the Codex App, go to **Plugins** in the sidebar, find Trustabl under the Security category, and click **+**. **Register the MCP server** so Codex can call `mcp__trustabl__scan`. Add to `~/.codex/config.toml`: ```toml [mcp_servers.trustabl] command = "trustabl" args = ["mcp"] ``` **How it works.** Codex reads [`.codex-plugin/plugin.json`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/.codex-plugin/plugin.json), which points `"skills": "./skills/"`. Codex loads the `trustabl-scan` and `trustabl-enrich` skills from that directory automatically โ€” no explicit invocation step required. Skills trigger when you write or modify agent, tool, or MCP-server code, and Codex applies findings via `trustabl-enrich`. The MCP tool is named `mcp__trustabl__scan` โ€” the same name as in Claude Code and Gemini CLI. To enable subagent delegation in Codex (used by `trustabl-enrich` for parallel file edits), set `multi_agent = true` in `~/.codex/config.toml`. ### "rules are newer than this Trustabl build" Trustabl loads rules **forward-compatibly**. If the resolved pack targets a newer rule-schema version than your binary understands, the scan still runs: it evaluates every rule your build *can* understand and **skips** the rest, warning on stderr (and recording the skipped rule IDs on `ScanResult.RulesSkipped`): ``` warning: the rules target schema version 13 but this Trustabl build supports up to 12; 2 rule(s) newer than this build were skipped. Upgrade Trustabl to evaluate them. ``` The same per-rule skip happens for any *individual* rule that references a `scope`, an `applies_to` value, or a predicate your build does not understand โ€” that rule is dropped while its siblings still run, so a newer rules release never forces a lockstep binary upgrade. Every skip is also surfaced **in the report itself** as a single `META-005` info finding ("N rules require a newer Trustabl engine"), so a degraded scan is never mistaken for a clean one. A *malformed* rule your build does understand (a missing field, a bad value) is **not** forward-skipped โ€” it still hard-fails the load, so real authoring errors are never silently dropped. To evaluate the skipped rules, **upgrade Trustabl** to a build whose `SupportedSchemaVersion` (see `internal/rules/schema_version.go`) covers the pack. No action is needed if you're comfortable running the subset. The scan only **fails** (exit 2) when nothing usable remains: - **"all rules require a newer engine schema"** โ€” *every* rule is too new for your build, so there is nothing to run. Upgrade Trustabl, or pin an older rules branch/tag your build fully understands (`--rules-ref` resolves branches and tags only, not raw commit SHAs, so a compatible ref must already exist): ```bash trustabl scan ./repo --rules-ref ``` - **"no usable rules manifest"** โ€” the pack's `manifest.yaml` is missing, unparseable, or declares a non-positive version (a corrupt/truncated pack). Run `trustabl rules pull` to refresh. - **"no usable rules found"** โ€” nothing cached and nothing fetchable (offline with a cold cache). Run `trustabl rules pull` while online. ## Where the code lives | Pipeline node | Code path | | ------------------ | ---------------------------------------- | | Importer | `internal/ingestion/importer.go` | | Normalizer (recon) | `internal/ingestion/normalizer.go` | | Discovery (Python AST + markdown/JSON) | `internal/analysis/discovery.go`, `agents.go`, `hosted_tools.go`, `mcp_servers.go`, `adk_agents.go` (Python AST); `subagents.go`, `markdown_agents.go`, `skills.go`, `slash_commands.go` (markdown frontmatter); `plugins.go`, `claude_settings.go` (JSON) | | TypeScript discovery | `internal/analysis/ts_discovery.go`, `ts_agents.go`, `ts_mcp_servers.go`, `ts_handler_facts.go`, `ts_openai_tools.go`, `ts_openai_agents.go`, `ts_openai_hosted_tools.go`, `ts_openai_mcp_servers.go`, `ts_openai_guardrails.go`, `ts_openai_sessions.go`, `ts_adk_tools.go`, `ts_adk_agents.go`, `ts_adk_hosted_tools.go`, `astutil/ts.go` | | Detector runtime | `internal/analysis/detectors/` | | Rule source | `internal/rulesource/` (git fetch + cache + schema-version gate) | | Detector rules | external `agent-reliability-rules` repo (tests: `testdata/rules-fixture/`) | | Rule engine | `internal/rules/{schema,loader,evaluator,predicates,rule_detector}.go` | | Scoring engine | `internal/analysis/scoring.go` | | Report renderer | `internal/review/diff.go` (human), `internal/sarif/render.go` (SARIF), JSON marshal in `cmd/trustabl` | | LLM config | `internal/llm/` (key storage ยท masking ยท validation) | Rule packs live in the separate `agent-reliability-rules` git repository (grouped `{claude_sdk,openai_sdk,google_adk,mcp}/`), resolved at scan time rather than embedded in the binary. Naming convention: `CSDK-NNN` for Claude Agent SDK rules (CSDK-0xx tool-scope, CSDK-1xx agent + subagent-scope), `OAI-NNN` for OpenAI Agents SDK rules, `ADK-NNN` for Google ADK rules, `MCP-NNN` for the dedicated MCP tool-scope pack. See [ARCHITECTURE.md ยง 2 โ€” steps 3โ€“4](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/ARCHITECTURE.md#2-pipeline) for the shipped rule table and [COVERAGE.md](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/COVERAGE.md) for per-SDK recognition detail. ## Testing `testdata/corpus/` holds real-world agent code (Claude SDK demos, OpenAI Agents SDK demos, Google ADK demos, a TS Claude SDK fixture) โ€” a corpus, not a controlled fixture, so well-written agents won't trigger most rules and that's correct. See [`testdata/corpus/PROVENANCE.md`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/testdata/corpus/PROVENANCE.md) for upstream sources and licenses of each example. Per-rule fire/silent correctness lives in `internal/rules/policies_test.go`; the end-to-end sweep in `internal/scanner/scanner_test.go` only asserts the scanner doesn't crash on real-world inputs. A labelled 20โ€“40 real-agent-repo corpus is the detection-quality target (see [ARCHITECTURE.md ยง 10](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/ARCHITECTURE.md#10-what-is-intentionally-out)); the current tests are regression coverage, not detection-quality measurement. ## Privacy & telemetry Trustabl optionally collects anonymous usage data โ€” which SDKs are scanned, scan duration, which rules fire โ€” to guide product direction. **No source code, file paths, repo names, or finding details are ever sent.** Telemetry is **off by default**; on your first interactive scan, Trustabl asks you to choose a level. On a panic, Trustabl writes a scrubbed crash report to `~/.config/trustabl/crash-.log` and, only in an interactive terminal, offers to send it anonymously or open a pre-filled GitHub issue โ€” otherwise nothing is transmitted. There is no auto-send: the default is always silence, and sending is an explicit per-crash choice. The report contains the panic message (with common secret shapes redacted best-effort) and stack frames; no source code, file contents, or argument values are included. Three levels are available: - **Disabled** โ€” no data sent (default) - **Minimal** โ€” CLI version and scan outcome only - **Full** โ€” anonymous usage stats ```sh trustabl telemetry off # disable trustabl telemetry minimal # version and outcome only trustabl telemetry full # full anonymous usage stats export TRUSTABL_TELEMETRY=0 # or disable for the current shell session trustabl telemetry status # show current level and its source ``` The full event schema โ€” every event name and every property, verbatim โ€” is at [TELEMETRY.md](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/TELEMETRY.md) (and at [trustabl.ai/telemetry](https://trustabl.ai/telemetry) once the site is live). That page is kept in sync with the code; stale docs are treated as a defect. ## Community Join the [Trustabl Discord](https://discord.gg/G6gM8nKxPg) to ask questions, share feedback, and follow development. ## License Apache-2.0. See [`LICENSE`](https://github.com/trustabl/agent-reliability-analyzer/blob/HEAD/LICENSE).