grill-me
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate clarifying questions and refine task descriptions for a downstream orchestrator. While this creates a potential surface for indirect injection, the skill acts primarily as a conversational guide.
- Ingestion points: Processes feature requests and user responses in the main interaction thread.
- Boundary markers: The instructions do not explicitly require delimiters (like triple backticks or XML tags) when incorporating user answers into the final orchestrator dispatch prompt.
- Capability inventory: The skill itself only produces text output; it has no file-system, network, or code execution capabilities.
- Sanitization: No explicit sanitization of user-provided input is specified before it is folded into subsequent prompts.
Audit Metadata