grill-me
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to "explore the codebase" to answer questions. This creates a surface where the agent processes data from the local environment which could contain malicious instructions.
- Ingestion points: Local files within the codebase (SKILL.md).
- Boundary markers: None specified to delineate project content from agent instructions.
- Capability inventory: Read access to local codebase files.
- Sanitization: No sanitization or validation of the codebase content is requested before processing.
Audit Metadata