teach
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of natural language instructions and configuration metadata. It does not perform any inherently dangerous operations such as file system modifications or external network requests.
- [NO_CODE]: No executable scripts, binaries, or compiled code are present in the skill files.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it is designed to process and explain external technical content.
- Ingestion points: The skill reads a "body of work" (code or text) provided by the user in the conversation context.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the ingested data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill invokes peer skills (how, why, unslop) and utilizes an image-generation tool to create diagrams.
- Sanitization: There is no evidence of input sanitization or validation of the content being processed for explanation.
Audit Metadata