teach
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill operates as an interactive teaching session that ingests user responses and external information from research tools, creating a surface for indirect prompt injection.
- Ingestion points: User input from learners answering Socratic questions or quizzes, and external content fetched through the referenced
researcherskill during Phase 2 (Plan) and error-checking steps. - Boundary markers: The skill does not define specific delimiters for separating user-provided answers or retrieved research data from its internal reasoning instructions.
- Capability inventory: The skill uses research capabilities, visualization tools, and interactive quiz interfaces as defined in the
Capability discoveryandTeachsections. - Sanitization: There are no instructions for sanitizing or escaping the content retrieved from external research tasks or user inputs before the agent incorporates them into the teaching flow.
Audit Metadata