grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from the local codebase and documentation files to guide its design review sessions. This ingestion of untrusted project data creates a surface for indirect prompt injection.
- Ingestion points: codebase files,
CONTEXT.md, and ADR files (SKILL.md). - Boundary markers: None identified to separate data from instructions.
- Capability inventory: Reads codebase and writes/updates documentation files (SKILL.md).
- Sanitization: No content sanitization or validation logic is defined.
Audit Metadata