grill
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions require the agent to find facts by reading from the repository and following project guides. This creates an ingestion surface for potentially untrusted data that could contain malicious instructions.
- Ingestion points: Files within the repository and project-specific guides like AGENTS.md.
- Boundary markers: No specific delimiters or instructions to ignore embedded commands in the repo data are provided.
- Capability inventory: The agent is authorized to read repository files and subsequently implement design changes or generate planning documents.
- Sanitization: There is no evidence of sanitization or filtering logic for the data retrieved from the repository.
- [NO_CODE]: The skill is a set of markdown instructions for agent behavior and does not include any accompanying scripts, shell commands, or dependencies.
Audit Metadata