ui-ux-scan
Pass
Audited by Gen Agent Trust Hub on Jul 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs its stated purpose of UI/UX analysis using standard Playwright browser tools without malicious intent.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes data from external websites. This is inherent to the tool's function and is documented here for completeness. 1. Ingestion points: External website data is retrieved via mcp__playwright__browser_snapshot and browser evaluation scripts in SKILL.md. 2. Boundary markers: No explicit delimiters or instructions are provided to the agent to distinguish between the scan instructions and content from the target website. 3. Capability inventory: The skill utilizes Playwright tools for navigation, screenshotting, and DOM snapshotting. 4. Sanitization: Content retrieved from external pages is analyzed directly by the agent without a prior sanitization or filtering step.
Audit Metadata