eli5
Pass
Audited by Gen Agent Trust Hub on Sep 7, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a simple persona for educational purposes without any malicious instructions.
- [NO_CODE]: The skill consists entirely of a markdown prompt and does not include any scripts or binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill operates on user-provided concepts, which represents a potential surface for indirect prompt injection. * Ingestion points: User concepts processed by the AI teacher in SKILL.md. * Boundary markers: None present. * Capability inventory: No tools or scripts are associated with this skill. * Sanitization: None.
Audit Metadata