teach
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions involve reading from the user's repository to understand context and domain vocabulary to personalize lessons.
- Ingestion points: User interaction and repository file inspection (SKILL.md).
- Boundary markers: None mentioned.
- Capability inventory: File read and write operations for state tracking within the
.scratch/learning/directory (SKILL.md). - Sanitization: Not explicitly defined.
Audit Metadata