llms.txt git:20260608.1fbc96cA

Immutable. This exact content never changes and is served at /api/v1/blob/368a538eeb2f3ad3.

# Trustabl

> Trustabl is a single-binary, read-only static analyzer for agent-SDK
> repositories. It discovers a repo's agent/tool inventory via tree-sitter,
> runs YAML-defined detection rules against it, and reports reliability and
> safety weaknesses as a human summary, JSON, or SARIF. A scan writes nothing
> into the scanned repo.

Key facts an LLM should know before reasoning about this project:

- **Scope.** CLI only — no web app, no API server, no artifact generation or
  remediation. It detects and reports; it does not modify the scanned repo.
- **SDK/language coverage.** Claude Agent SDK (Python + TypeScript), OpenAI
  Agents SDK (Python), Google ADK (Python), MCP (Python tool registrations),
  and an OpenShell shell-invocation risk surface. TypeScript discovery is wired
  for the Claude SDK; no TS-language rules ship yet.
- **Detection model.** Every rule fires at exactly one of five scopes —
  `tool`, `agent`, `subagent`, `skill`, or `repo` — and receives a typed input.
  Agent-scoped findings attribute to a specific agent, not the whole repo.
- **Rules are not embedded in the binary.** They live in a separate git
  repository (`trustabl-rules`) and are resolved at scan time, cached locally
  with offline fallback and a schema-version gate.
- **Determinism is a contract.** Identical inputs produce an identical scan ID
  (which folds in the resolved rules SHA) and a byte-stable report.
- **Build constraint.** tree-sitter is a C library, so `CGO_ENABLED=1` is
  required to build.

## Docs

- [README](https://raw.githubusercontent.com/trustabl/trustabl/main/README.md): external-facing intro — what it does, install, usage, CLI flags, exit codes, output formats.
- [ARCHITECTURE](https://raw.githubusercontent.com/trustabl/trustabl/main/ARCHITECTURE.md): the implementer's reference — package layout, the scan pipeline (recon → inventory → policy selection → analysis → scoring → review), the data model, the rules engine, and the determinism contract.
- [COVERAGE](https://raw.githubusercontent.com/trustabl/trustabl/main/COVERAGE.md): at-a-glance matrix of which SDKs and languages are scanned, analysed, and detected against, plus what is parsed per SDK and the known gaps.
- [CHANGELOG](https://raw.githubusercontent.com/trustabl/trustabl/main/CHANGELOG.md): notable changes per release (Keep a Changelog format).

## Optional

- [Rules repository](https://github.com/trustabl/trustabl-rules): the external YAML rule packs the engine pulls at scan time — the production source of detection rules.
- [LICENSE](https://raw.githubusercontent.com/trustabl/trustabl/main/LICENSE): Apache-2.0.