teach
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains purely instructional content to guide the agent in structuring and delivering technical explanations.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and explain external data such as source code, version control diffs, and repository history, which is a standard surface for indirect prompt injection. 1. Ingestion points: Source code files, version control diffs, and repository history via the SKILL.md instructions. 2. Boundary markers: No specific delimiters or safety instructions regarding untrusted content are included in this specific file. 3. Capability inventory: The skill allows reading repository files and generating diagrams or images. 4. Sanitization: The instructions do not specify any sanitization or escaping of the processed external data.
Audit Metadata