correct
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and analyze untrusted external data, including commit messages, reverts, review comments, and existing agent instruction files. This creates a surface for indirect prompt injection where an attacker could influence the agent's behavior by embedding instructions within repository metadata.
- Ingestion points: Recent commits, reverts, review comments, and project files.
- Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the analyzed data from the agent's instructions.
- Capability inventory: The skill implies general repository management capabilities including file reading, file writing, and potentially running lints or tests.
- Sanitization: No explicit sanitization or validation of the analyzed data is mentioned.
Audit Metadata