grill-me
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No patterns of instruction override, safety bypass, or system prompt extraction were found. The instructions focus entirely on the intended design review task.
- [DATA_EXFILTRATION]: No network-related commands (curl, wget) or attempts to read sensitive files (e.g., .ssh, .aws) were detected.
- [EXTERNAL_DOWNLOADS]: The skill contains no references to external scripts, remote code, or third-party package installations.
- [COMMAND_EXECUTION]: There are no shell commands, scripts, or system-level operations requested within the instructions.
- [SAFE]: The instruction to explore the codebase is a standard capability of the underlying agent and is used here to inform the interview process rather than for malicious data gathering.
Audit Metadata