review
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill provides a protocol for agent communication and synthesis during code reviews. No malicious behaviors, obfuscation, or unauthorized access attempts were detected.
- [PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted code from external sources such as Git commits or pull requests, creating a surface for indirect prompt injection. The risk is mitigated by the collaborative 'Team' protocol which requires multiple agents to cross-examine findings and resolve conflicts. * Ingestion points: Git commits and pull request data via CLI flags. * Boundary markers: None specified in the instructions. * Capability inventory: The skill is focused on analysis and synthesis; no dangerous tool execution or network writes are defined in this file. * Sanitization: No explicit sanitization of the input code is described.
- [NO_CODE]: The skill consists entirely of markdown instructions and metadata. No executable scripts or configuration files are included in the analyzed content.
Audit Metadata