scientific-figure
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for the agent to use specific image generation tools (OmniScholar and Ai4Scholar) in a controlled manner, requiring explicit capability discovery before execution.- [SAFE]: The workflow emphasizes data privacy and security by instructing the agent to never substitute private images, restrict local references to configured workspace roots, and avoid exposing signed URLs.- [SAFE]: The instructions focus on scientific accuracy and integrity, clearly stating that generated content is for drafting purposes and not experimental evidence.- [SAFE]: No malicious patterns, such as prompt injection, unauthorized data access, or obfuscation, were identified in the skill content.
Audit Metadata