usability-psychologist
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to evaluate external UI flows and UX content, which represents an attack surface for indirect prompt injection if malicious instructions are embedded in the analyzed data. * Ingestion points: External UI descriptions, code snippets, or user feedback processed during evaluation. * Boundary markers: None present in the instructions. * Capability inventory: The skill is restricted to reasoning and generating text output; it lacks any system command execution, file modification, or network access capabilities. * Sanitization: No sanitization or filtering logic is defined for the external content it reviews.
Audit Metadata