review-pr

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from pull request diffs and specification files, which could theoretically contain malicious instructions targeting the reviewer sub-agents.
  • Ingestion points: Pull request diffs, commit messages, and external specification files identified in SKILL.md.
  • Boundary markers: Sub-agent prompts in SKILL.md (Step 4) define specific tasks and constraints to limit the scope of processing.
  • Capability inventory: Executes git commands and publishes review comments to GitHub PRs as defined in SKILL.md.
  • Sanitization: The skill does not explicitly sanitize or escape the content of the diffs or specs before they are processed by the LLM sub-agents.
  • [COMMAND_EXECUTION]: The skill uses local git commands to perform its primary function of code analysis.
  • Evidence: SKILL.md includes instructions to run git diff, git log, and git rev-parse to compare code changes against a fixed point.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 02:59 AM
Security Audit — agent-trust-hub — review-pr