explain-concept
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by processing external learner data and interacting with code execution tools.
- Ingestion points: The agent is instructed to establish the learner's starting knowledge, questions, and decisions as the basis for the explanation (SKILL.md).
- Boundary markers: The instructions do not provide or suggest the use of delimiters (such as XML tags or triple backticks) to separate untrusted learner input from the agent's core instructions.
- Capability inventory: The skill explicitly directs the agent to check arithmetic and execute small code examples using available tools (SKILL.md).
- Sanitization: There are no instructions to sanitize, escape, or validate the code or concepts provided by the learner before processing them with tools.
Audit Metadata