design-review

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: No malicious patterns, suspicious remote code execution, or unauthorized network operations were identified.
  • [NO_CODE]: The skill consists entirely of instructional markdown and metadata without any accompanying scripts or executable files.
  • [COMMAND_EXECUTION]: The skill utilizes browser automation tools such as Playwright or Chrome MCP to interact with web pages for design auditing.
  • [PROMPT_INJECTION]: Indirect prompt injection surface analysis: 1. Ingestion points: Untrusted external web content via browser tools. 2. Boundary markers: The instructions do not specify delimiters to separate page content from instructions. 3. Capability inventory: Browser navigation, DOM reading, screenshot capture, and local file writing. 4. Sanitization: No specific filtering or sanitization of external content is defined.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 04:21 PM