teach-me
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized data access were identified. The skill logic is focused entirely on educational interaction and follows safe data handling practices.
- [DATA_EXFILTRATION]: The skill manages the creation of learning records and documentation. It explicitly instructs the agent to follow existing user preferences and warns against committing personal learning artifacts to shared or team repositories without consent, demonstrating a security-conscious approach to data management.
- [PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection, which is handled with a safe classification due to the limited capability set.
- Ingestion points: User dialogue and answers provided during interactive tutoring sessions (SKILL.md).
- Boundary markers: No explicit delimiters are used to wrap user input when processing or saving it.
- Capability inventory: File system access is utilized to save and update markdown-based learning records and walkthroughs (durable-learning.md, walkthrough-doc.md).
- Sanitization: No specific content validation or escaping is implemented for user-provided data before it is written to files.
Audit Metadata