aireview
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of natural language instructions for a code review persona and does not include any executable scripts, shell commands, or network operations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data in the form of source code and pull request diffs.
- Ingestion points: Processes code from commits, branch files, and pull requests (SKILL.md Objectives).
- Boundary markers: None explicitly defined for the analyzed code content.
- Capability inventory: Uses information gathering tools and delegates tasks to 'Implementor' and 'Verifier' agents.
- Sanitization: No explicit sanitization or escaping of reviewed code content is described.
Audit Metadata