grill-with-docs
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to scan the repository to identify relevant files, modules, schemas, and documentation. This is a standard read-only discovery process intended to gather context for the 'grilling' session.
- [DATA_EXFILTRATION]: There are no instructions or patterns indicating that data is being sent to external servers. The skill operates locally on the provided codebase.
- [PROMPT_INJECTION]: The instructions use strong directive language such as 'Interview me relentlessly' and 'Challenge against the glossary,' but these are within the scope of its intended educational and analytical function and do not attempt to bypass core AI safety guidelines.
- [REMOTE_CODE_EXECUTION]: No remote scripts, package installations, or dynamic code execution patterns were detected.
Audit Metadata