teach
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as an orchestrator for explaining technical content, utilizing delegated sub-tasks (
howandwhyskills) and internal tools for visualization (Mermaid diagrams, image generation, and device previews). - [SAFE]: No evidence of prompt injection or attempts to bypass safety filters was found; instructions are strictly task-oriented and focus on clear communication.
- [SAFE]: Data access is limited to conversation context (
t3_thread_read,t3_thread_search) and the target body of work, with no patterns suggesting exfiltration of sensitive files or credentials. - [SAFE]: The use of internal delegation (
delegate_task) and tool execution (preview_*,device_*) aligns with the stated purpose of technical explanation and walkthroughs.
Audit Metadata