grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Jun 25, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions and configuration are purely focused on documentation and domain modeling. No malicious patterns, external downloads, or unauthorized command executions were found.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes data from the local codebase. Ingestion points: Ingests content from source files, CONTEXT.md, and ADRs (SKILL.md). Boundary markers: Instructions do not specify delimiters to separate codebase content from the agent's internal instructions. Capability inventory: The skill can read any file in the repository and write to documentation files (SKILL.md, ADR-FORMAT.md). Sanitization: No sanitization or validation of ingested codebase content is performed before processing.
Audit Metadata