teach
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions focus entirely on pedagogical methods and coordinating internal agent capabilities for explanation. No malicious patterns, obfuscation, or unauthorized access attempts were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests technical data for analysis. Ingestion points: Technical documentation, code, and diffs provided by the user (SKILL.md). Boundary markers: None explicitly defined in the instructions. Capability inventory: Natural language explanation and image/diagram generation; no network or file-system write access. Sanitization: Not specified. The lack of dangerous output capabilities effectively neutralizes the risk from this ingestion surface.
Audit Metadata