grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided designs to generate documentation (ADRs and glossaries). This establishes a surface where instructions embedded within the processed design could potentially influence the agent's behavior during the interview or document generation process.
- Ingestion points: The skill processes user-supplied plans or designs as mentioned in the description.
- Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the input data.
- Capability inventory: The agent invokes the "grill-me" and "domain-modeling" tools and writes documentation files (ADRs and glossary).
- Sanitization: No input sanitization or validation mechanisms are defined for the design content.
- [NO_CODE]: The skill does not include any scripts, executable code, or shell commands, relying entirely on natural language instructions and tool invocations.
Audit Metadata