master-help
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust 'CRISIS FIRST' safety protocol, explicitly instructing the agent to direct users to professional emergency services and crisis hotlines (e.g., 120, 110, 911, 988) if self-harm or acute mental health issues are detected.
- [SAFE]: The skill operates primarily as a router (meta-skill), mapping user queries to specific teaching modules. It explicitly forbids the agent from providing doctrinal advice or spiritual certifications directly, deferring these tasks to specialized sub-skills.
- [SAFE]: Network activity is restricted to reading local configuration files (e.g.,
~/.claude/skills/master-*/meta.json) to determine routing keywords, which is a standard operational pattern for this type of agent skill. - [SAFE]: No obfuscation, data exfiltration, or unauthorized command execution patterns were detected. The use of internal shell commands (e.g.,
master-skill recommend) is scoped to the skill's intended functionality and occurs within the controlled environment.
Audit Metadata