grill-me

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to explore the local codebase and gather context for the interview process.
  • [DATA_EXPOSURE]: The skill reads from internal rule files located in .claude/skills/control-tower/rules/ to inform its questioning logic.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the codebase and user input to generate documentation (common.md, atdd.md). While no explicit sanitization is mentioned, the risk is limited by the skill's specific purpose of document generation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 01:53 AM
Security Audit — agent-trust-hub — grill-me