grill-me
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown instructions and JSON evaluation data. It does not include any scripts, binaries, or configuration files that execute code.
- [NO_CODE]: No programming languages (Python, Node.js, etc.) or package managers are utilized. The skill functions solely through the agent's natural language processing capabilities.
- [PROMPT_INJECTION]: The instructions do not contain patterns designed to bypass safety filters or extract system prompts. While the role is described as 'adversarial', this is limited to technical critique of user-provided plans.
Audit Metadata