grill-me
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [No Code] (SAFE): This skill consists entirely of natural language instructions and metadata. No executable scripts, binaries, or configuration files are present.
- [Prompt Injection] (SAFE): The prompt establishes a persona for product discovery and does not contain directives to bypass safety protocols or override system instructions.
- [Indirect Prompt Injection] (SAFE): The skill ingests user input via standard chat or the request_user_input tool. Mandatory Evidence Chain: 1. Ingestion points: SKILL.md (via tool and chat). 2. Boundary markers: Absent. 3. Capability inventory: No scripts or tools with file-write, network, or execution capabilities are included in the skill package. 4. Sanitization: Not explicitly implemented in the prompt; relies on the base LLM's safety filters.
Audit Metadata