ui-visual-validator
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of behavioral instructions and persona descriptions. It does not include any scripts, binary files, or commands that interact with the host system or network.
- [PROMPT_INJECTION]: The skill includes instructions to process external visual data and design requirements. This creates a surface for indirect prompt injection. However, the instructions strongly emphasize skepticism and the prioritization of direct visual observation over provided code or hints, which effectively mitigates the risk. Ingestion points: Visual evidence (screenshots) and design goals. Boundary markers: Required output prefix ('From the visual evidence, I observe...'). Capability inventory: None (no system-level capabilities requested or used). Sanitization: None described for visual inputs.
Audit Metadata