grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze untrusted content from the repository's codebase and documentation files. While this creates an indirect prompt injection surface, the risk is negligible as the skill's capabilities are limited to documentation maintenance and user interviewing.
- Ingestion points: Reads CONTEXT.md, CONTEXT-MAP.md, ADRs, and codebase source files.
- Boundary markers: None identified for ingested codebase content.
- Capability inventory: Limited to file-read and file-write operations for updating documentation.
- Sanitization: No explicit sanitization or filtering of codebase content is defined.
Audit Metadata