reviewing-pull-requests

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill utilizes standard, well-known command-line utilities (git, gh) to retrieve repository information and code diffs. These actions are appropriate for the skill's primary function of code review.
  • [INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted data by reviewing code changes and pull request content submitted by potentially external contributors.
  • Ingestion points: The skill reads content from the output of git diff --name-only and gh pr view as specified in Step 1 of the workflow.
  • Boundary markers: The workflow uses specific markdown headers (e.g., 'PR Review Summary', 'Critical Issues') to structure and delimit the findings from different specialized agents.
  • Capability inventory: The skill uses repository inspection tools (git, gh) but does not include file-write or arbitrary network execution capabilities.
  • Sanitization: No explicit sanitization or filtering of the pull request content is defined, relying on the agent's internal logic to process the diffs safely.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 08:32 AM
Security Audit — agent-trust-hub — reviewing-pull-requests