receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines behavioral and technical guidelines for processing code reviews. No malicious instructions, obfuscation, or data exfiltration patterns were detected.
- [COMMAND_EXECUTION]: The skill references the use of the GitHub CLI (
gh api) to respond to pull request comments. This is a standard administrative task for software development and does not involve arbitrary or dangerous command execution. - [PROMPT_INJECTION]: The skill incorporates safeguards against malicious or incorrect external input. It instructs the agent to be skeptical of external reviewers, verify suggestions against the actual codebase, and prioritize technical correctness over blind implementation. This effectively manages the attack surface associated with indirect prompt injection from external review comments.
Audit Metadata