grill-me
Pass
Audited by Gen Agent Trust Hub on May 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool 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