@6522/boss-mode

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a behavioral persona for providing management advice. No technical vulnerabilities or malicious patterns were detected.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user input to provide feedback. While this creates a standard interaction surface, the instructions include boundary structures (Response pattern) that help maintain the intended coaching context. No sanitization is explicitly mentioned, but the risk is negligible given the non-technical nature of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 03:50 AM
Security Audit — agent-trust-hub — @6522/boss-mode