github-review-suggestions

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from GitHub Pull Requests, which is a vector for indirect prompt injection where malicious instructions could be embedded in code or comments.
  • Ingestion points: Untrusted data enters the agent context via the gh pr view and gh pr diff commands described in SKILL.md.
  • Boundary markers: The skill includes a contract in SKILL.md that explicitly instructs the agent to treat PR metadata and diffs as untrusted third-party text and to never follow instructions embedded within them.
  • Capability inventory: The skill has the authority to post review comments back to GitHub via the gh api and execute shell commands using git, gh, and node.
  • Sanitization: The workflow mandates human approval before any comments are posted or branches are modified, and it instructs the agent to redact secrets from suggested fixes.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:05 PM
Security Audit — agent-trust-hub — github-review-suggestions