grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses local vault files to ground domain modeling and interviews, creating an attack surface where untrusted data could influence agent output.
- Ingestion points: The skill reads from
.agent/context/knowledge-vault.md,docs/agents/knowledge-vault.md, and user research notes. - Boundary markers: No delimiters or instructions to ignore embedded prompts are provided for the vault content.
- Capability inventory: The skill writes decisions, ADRs, and glossary terms to
CONTEXT.md. - Sanitization: There is no evidence of sanitization or filtering of the ingested content before it is used to generate documentation.
- [NO_CODE]: The skill contains only instructions and markdown configuration, without any executable scripts or binary files.
Audit Metadata