grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates a workflow where the agent reads existing code and documentation to update or create new files like CONTEXT.md and ADRs. This ingestion of potentially untrusted data from the workspace constitutes an indirect prompt injection surface.
- Ingestion points: The agent is instructed to inspect existing context documents and source code (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the ingested files.
- Capability inventory: The skill is authorized to perform file writes to CONTEXT.md and generate new Architecture Decision Record (ADR) files (SKILL.md).
- Sanitization: There is no mention of sanitizing or filtering content retrieved from the files or user feedback.
Audit Metadata