ship-learn-next

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (SAFE): The skill ingests untrusted data from user-provided files to generate plans. While an injection surface exists, the functionality is restricted to reading content and writing Markdown files. | Ingestion points: User-provided file paths for educational content. | Boundary markers: Absent. | Capability inventory: Read and Write tools. | Sanitization: Standard LLM processing.
  • [General Security] (SAFE): The skill performs legitimate file operations as described in its purpose. No evidence of command execution, persistence mechanisms, or data exfiltration to external domains was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 11:27 PM