refactor-review
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
gitfor repository management andpython3to run a local ledger validation script. It also executes project-specific test commands derived from configuration files and project manifests. - [INDIRECT_PROMPT_INJECTION]: The skill processes project data files which may contain malicious content. It mitigates this by instructing the agent to treat all ingested content as data rather than instructions, specifically barring the execution of commands found in prose.
- [SAFE]: The included utility script
scripts/ledger.pyis a safe Python script that uses only standard library modules and has no network or unauthorized file access logic.
Audit Metadata