grill-me
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the codebase to answer questions, creating an injection surface.\n- Ingestion points: The agent explores the local codebase to find answers.\n- Boundary markers: There are no instructions to treat codebase content as data or to ignore instructions found within files.\n- Capability inventory: File system read access is used to explore the project.\n- Sanitization: No sanitization of codebase content is performed before processing.
Audit Metadata