review-local-changes
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the local development environment, creating a potential surface for indirect prompt injection.
- Ingestion points: Reads all local changes, including commits, staged, unstaged, and untracked files.
- Boundary markers: No specific delimiters or safety instructions are defined to separate code data from agent instructions.
- Capability inventory: The skill allows modifying code files to fix findings and executing verification commands.
- Sanitization: No content sanitization or escaping mechanisms are described for the ingested source code.
Audit Metadata