web-design-reviewer
Pass
Audited by Gen Agent Trust Hub on May 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation recommends using the official @playwright/mcp package from Microsoft to enable browser automation features.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes untrusted data from external websites to inform its code-fixing logic.
- Ingestion points: The skill retrieves website content and DOM structure via browser automation tools described in
SKILL.md. - Boundary markers: None identified for the ingested DOM snapshots.
- Capability inventory: The agent has file read/write and code search capabilities as listed in the
Required Capabilitiessection ofSKILL.md. - Sanitization: No specific sanitization of external website content is mentioned before it is processed for visual inspection and automated fixes.
Audit Metadata