learn-new-topic
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns detected. The skill functions as a navigational orchestrator for educational content.
- [PROMPT_INJECTION]: Instructions focus strictly on pedagogical routing and do not attempt to manipulate agent behavior or bypass safety constraints.
- [DATA_EXFILTRATION]: No network activity or sensitive file access was identified.
- [REMOTE_CODE_EXECUTION]: The skill does not download or execute external code; it only references internal agent tools.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided topics to sequence other learning skills (Ingestion: user input in conversation; Boundaries: absent; Capabilities: skill delegation; Sanitization: absent). This setup presents minimal risk as it acts as a high-level router.
Audit Metadata