receiving-code-review

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for ingesting and acting upon feedback from external reviewers, which constitutes a surface for indirect prompt injection. The skill mitigates this by requiring the agent to technically verify all suggestions against the codebase reality before implementation.
  • Ingestion points: External reviewer feedback processed by the agent in SKILL.md.
  • Boundary markers: Absent; however, the agent is instructed to restate requirements in its own words.
  • Capability inventory: Includes grep for codebase searching and gh api for GitHub communication.
  • Sanitization: None; relies on the agent's logical evaluation and verification steps.
  • [COMMAND_EXECUTION]: The skill references the use of grep and gh api tools for development tasks.
  • The grep command is used locally to check for code usage (YAGNI check).
  • The gh api command is used to reply to GitHub pull request comments at repos/{owner}/{repo}/pulls/{pr}/comments/{id}/replies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:57 PM
Security Audit — agent-trust-hub — receiving-code-review