receiving-code-review

Pass

Audited by Gen Agent Trust Hub on May 7, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill provides guidelines for technical skepticism and verification during code reviews. It directs the agent to prioritize technical correctness over social compliance, which is a defensive measure against incorrect or malicious suggestions.
  • [COMMAND_EXECUTION]: The skill uses standard development tools like grep for codebase searches and the GitHub CLI (gh api) to respond to pull request comments. These operations are restricted to the context of a software development workflow.
  • [PROMPT_INJECTION]: The skill processes untrusted input in the form of code review feedback, creating a surface for indirect prompt injection.
  • Ingestion points: Code review feedback from external reviewers and human partners entering the agent context via SKILL.md instructions.
  • Boundary markers: Absent; the instructions do not specify delimiters for the feedback content.
  • Capability inventory: The agent possesses file system search (grep), codebase modification, and repository API access capabilities.
  • Sanitization: Absent; the skill relies on the agent's technical evaluation and the mandate to "verify then implement" to mitigate risks.
Audit Metadata
Risk Level
SAFE
Analyzed
May 7, 2026, 09:48 AM
Security Audit — agent-trust-hub — receiving-code-review