grill-me

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is limited to high-level natural language instructions for a structured interview session. It contains no executable scripts, commands, or automation logic.
  • [NO_CODE]: No external dependencies, packages, or remote code patterns are present.
  • [DATA_EXFILTRATION]: The instructions explicitly forbid writing to project directories (".agents/projects/"), ensuring that the skill's activities remain within the immediate conversation context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 01:26 PM
Security Audit — agent-trust-hub — grill-me