quiz
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution were identified. The skill functions solely through abstract tools intended for educational assessment.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user responses to quizzes to update mastery levels, creating a surface for untrusted data. 1. Ingestion points: user quiz responses (SKILL.md). 2. Boundary markers: None specified. 3. Capability inventory: create_quiz and update_mastery tools. 4. Sanitization: None described in the instructions.
Audit Metadata