grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection due to its workflow of reading untrusted data.
- Ingestion points: Reads user plans, documents, and codebase files as defined in the workflow of SKILL.md.
- Boundary markers: Lacks explicit instructions or delimiters to isolate untrusted data from the agent's command context during processing.
- Capability inventory: Authorized to modify filesystem content, specifically updating CONTEXT.md and creating new ADR files in docs/adr/.
- Sanitization: No validation or sanitization of ingested content is performed before it is used to influence the generation of documentation.
Audit Metadata