no — deterministic offline scan; enrich uses your own key; telemetry opt-in
No. Skills (SKILL.md) teach the agent how to perform a task or workflow. Trustabl Agent Analyzer (TAA) makes the tools themselves reliable, safe, and production-ready. Skills focus on process. TAA focuses on resilience, validation, policy, observability, and supply-chain trust. The two are highly complementary — great skills need hardened tools underneath them.
Not for scanning. The analyzer is read-only and reports findings without changing your files. If you use trustabl enrich, it proposes a patch for review and only applies it when you choose --apply; it also creates a .trustabl.bak backup and skips stale fixes when the file has changed since the scan.
Most repositories can be scanned in seconds. Install the open-source Agent Reliability Analyzer, run trustabl scan . from your local repository, and review the findings—no account, GitHub connection, or code upload required. The time needed to apply fixes depends on the number and severity of the findings.
