grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied design plans to generate documentation such as Architectural Decision Records (ADRs) and glossaries. This represents an attack surface for indirect prompt injection.
- Ingestion points: User-provided designs and plans are processed via the instructions for grilling and domain-modeling.
- Boundary markers: The instructions do not specify delimiters or warnings to ignore instructions embedded within the user's design documents.
- Capability inventory: The skill is designed to generate documentation files based on the user-provided input.
- Sanitization: No sanitization or filtering of the user-provided content is defined in the instructions.
Audit Metadata