coding-level
Pass
Audited by Gen Agent Trust Hub on May 6, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security vulnerabilities were detected. The skill primarily functions by setting a configuration variable in a local file (
.claude/.ck.json) to adjust explanation verbosity. While it employs highly assertive instructional language (e.g., "MANDATORY IMPORTANT MUST ATTENTION") to enforce best practices like task planning and evidence citation, these are process-oriented directives that do not attempt to bypass safety guidelines or exfiltrate data.
Audit Metadata