tooluniverse
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill correctly implements a routing architecture that maps user keywords to specialized sub-skills for biological and chemical research.
- [SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized command execution was found.
- [SAFE]: The instructional language used, including markers like 'CRITICAL' and 'WARNING', serves to define the agent's core routing logic and does not attempt to bypass platform safety guidelines or extract system prompts.
- [SAFE]: The skill utilizes platform-standard tools ('Skill' and 'AskUserQuestion') and references internal documentation appropriately.
- [SAFE]: All identified sub-skills (e.g., 'tooluniverse-drug-research') are vendor-owned resources consistent with the skill's stated purpose.
Audit Metadata