grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process existing project documentation and user input to generate or update design artifacts.
- Ingestion points: The skill reads from "existing artifacts" and project-configured documentation (as described in SKILL.md and UPSTREAM.md) to extract terms and relationships.
- Boundary markers: The instructions do not define explicit delimiters (e.g., XML tags or clear separators) or specific warnings to ignore instructions embedded within the project files it reads.
- Capability inventory: Based on the instructions, the skill is tasked with creating and modifying files, specifically ADRs, glossaries, and domain-modeling artifacts.
- Sanitization: There is no evidence of sanitization, validation, or escaping of the content ingested from the project artifacts before it is processed by the agent.
Audit Metadata