ux-heuristics
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and reference templates for conducting UX audits. It does not include any executable scripts, tool configurations, or external dependencies.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it is designed to analyze potentially untrusted content such as user-provided interface designs or feedback. However, because the skill lacks any functional capabilities to perform network operations, write files, or execute commands, there is no path for exploitation. 1. Ingestion points: Interface designs and usability feedback provided by the user (SKILL.md). 2. Boundary markers: None identified in instructions. 3. Capability inventory: None. No tools or scripts are included or requested. 4. Sanitization: None identified.
Audit Metadata