evaluate
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains purely instructional content for performing user experience audits and heuristic evaluations without any executable code. \n- [SAFE]: No external dependencies, remote code execution, or network operations are present. \n- [SAFE]: No obfuscation techniques, such as Base64, zero-width characters, or homoglyph attacks, were found in the instructions or metadata. \n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied designs, which creates an inherent surface for indirect prompt injection. 1. Ingestion points: UX review requests and design descriptions in SKILL.md. 2. Boundary markers: None specified. 3. Capability inventory: Local file-writing for reporting results. 4. Sanitization: None described. The potential impact is minimized by the total absence of network access or shell command capabilities in the skill's instruction set.
Audit Metadata