review

Pass

Audited by Gen Agent Trust Hub on Aug 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a structured code review process that prioritizes security and correctness. It mandates a sensitive data scan using the safe-repo tool for every review pass.
  • [SAFE]: The orchestrator enforces a read-only execution policy for all sub-agents, explicitly prohibiting modifications, staging, or committing of code during the review phase.
  • [COMMAND_EXECUTION]: The skill uses standard development tools such as git and gh (GitHub CLI) to retrieve diffs and PR metadata. These are appropriate for its stated purpose as a code review orchestrator.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data in the form of git diffs and pull request content. While it lacks explicit boundary markers in the instruction set, the risk is mitigated by the read-only constraint and the use of specialized, fresh-context sub-agents for different review lenses, preventing cross-context contamination.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 23, 2026, 06:03 PM
Security Audit — agent-trust-hub — review