review

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes local Node.js scripts located in the .agents/scripts/ directory, specifically cooking.mjs, precheck.mjs, and spec-files.mjs, to automate status checking and specification parsing.
  • [COMMAND_EXECUTION]: The skill invokes git commands such as git rev-parse and git diff to determine the scope of changes and sets up a call to an external git-commit tool to handle repository updates upon successful review.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data from git diff outputs and project files (e.g., spec.md, Pn.md, ACCEPTANCE.md). This represents a potential surface where malicious instructions embedded in the code or documentation could attempt to influence the agent's review logic. Boundary markers are partially addressed by the strict sub-agent task templates provided in the reference files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 09:43 AM
Security Audit — agent-trust-hub — review