receiving-code-review
Pass
Audited by Gen Agent Trust Hub on Jun 21, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns such as credential theft, persistence, or unauthorized exfiltration were detected. The skill focuses on professional technical communication protocols.
- [NO_CODE]: The skill consists solely of markdown instructions and does not include any scripts, executable files, or third-party dependencies.
- [PROMPT_INJECTION]: The skill addresses the processing of external code review feedback, which is a potential surface for indirect prompt injection. The skill incorporates mitigation strategies such as technical verification and skepticism.
- Ingestion points: External code review feedback (SKILL.md).
- Boundary markers: Absent for input data, though the workflow requires restating requirements before action.
- Capability inventory: Potential use of grep for codebase analysis and GitHub API (gh api) for interaction.
- Sanitization: The instructions mandate a manual evaluation of the technical correctness of suggestions before implementation, which acts as a verification gate.
Audit Metadata