poteto-teach
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external "bodies of work" such as code, diffs, and subsystems to generate explanations, which constitutes an ingestion surface for potentially untrusted data.
- Ingestion points: The body of work (codebase content, git diffs) identified in SKILL.md for analysis.
- Boundary markers: The instructions do not define explicit delimiters or ignore-instructions for the content being explained.
- Capability inventory: The skill can read files, execute the how and why skills, use debuggers, and invoke an image-generation tool.
- Sanitization: No explicit sanitization or filtering of the input content is specified before it is processed by the agent.
Audit Metadata