teach-me
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and explain external data such as pull requests, ADRs, and code changes, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The skill processes current session changes, PR diffs, and other user-provided topics as ingestion points for the agent's context (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore commands embedded within the source artifacts being explained.
- Capability inventory: The skill utilizes standard chat output and a structured quiz harness; it does not involve subprocess execution, file writing, or network operations.
- Sanitization: There is no mention of sanitizing or filtering instructions that might be contained within the documents or code being analyzed.
Audit Metadata