code-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted code changes via Git, creating a surface for indirect prompt injection where instructions embedded in the reviewed code could attempt to influence the agent.
- Ingestion points: Code changes and Git history accessed via
git diffandgit showincode-reviewer-prompt.md. - Boundary markers: The skill employs a structured subagent prompt and explicit instructions to verify feedback against the codebase in
SKILL.md. - Capability inventory: The skill uses Git commands for repository inspection, writes review reports to a specific subdirectory, and uses a project-specific CLI tool (
ssf) to record results. - Sanitization: No specific technical sanitization is applied to the code content, relying instead on the agent's verification and technical rigor requirements.
Audit Metadata