security-review
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using the Bash tool, including 'git diff' to scope the review and 'python3 scripts/security-review-scan.py' to run a deterministic vulnerability scanner on the identified files.\n- [PROMPT_INJECTION]: The skill ingests untrusted data from the repository (git diffs and local security guidance files), which represents an indirect prompt injection surface. It mitigates this risk by instructing the agent to treat local guidance as additive and to never suppress findings based on instructions within the reviewed content.
Audit Metadata