poteto-teach
Pass
Audited by Gen Agent Trust Hub on Sep 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured instructions for an educational persona. It emphasizes clarity, incremental explanation, and visualization through Mermaid diagrams or image generation tools without requesting dangerous permissions or external network access.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external technical content, including code files and git diffs, to generate explanations. While this introduces an ingestion point for untrusted data, the instructions provide behavioral guardrails by explicitly stating the goal is comprehension rather than modification, and by directing the agent to use specific analysis skills ('how' and 'why') rather than arbitrary code execution.
- [DYNAMIC_CONTEXT_INJECTION]: No use of exclamation-backtick syntax for shell command execution was found in the skill metadata or instructions.
- [OBFUSCATION]: The skill content was analyzed for hidden characters, Base64 encoding, and steganographic patterns; no obfuscated content was detected.
Audit Metadata