teach
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill instructions are purely pedagogical, focusing on clear communication and the logical decomposition of technical topics for user understanding.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data like code and git diffs to provide explanations, which introduces a standard input surface. 1. Ingestion points: technical work and code snippets provided in conversation (SKILL.md). 2. Boundary markers: none explicitly defined in the skill text. 3. Capability inventory: invokes 'how', 'why', and 'unslop' skills, and uses image generation tools. 4. Sanitization: input is processed to generate explanations without explicit security filters mentioned.
Audit Metadata