Skills
Navigate
skills/galaxy-dawn/claude-scholar/web-design-reviewer/Gen Agent Trust Hub

web-design-reviewer

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes content from external, user-provided URLs, which introduces an attack surface for indirect prompt injection via malicious web content.
  • Ingestion points: External web content is ingested through browser_navigate and browser_snapshot tools as described in the Visual Inspection Phase of SKILL.md.
  • Boundary markers: Absent. The instructions do not define delimiters or warnings to ignore potential instructions embedded within the processed web pages.
  • Capability inventory: The skill possesses file system write access for applying design fixes and can perform broad code searches using grep_search and semantic_search.
  • Sanitization: Absent. No sanitization or validation of the retrieved DOM or page text is specified before processing.
  • [EXTERNAL_DOWNLOADS]: The skill documentation suggests downloading and executing a third-party tool for its browser automation capabilities.
  • Evidence: The 'Reference Implementation' section in SKILL.md recommends using npx -y @playwright/mcp@latest to set up the necessary browser interface.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 01:59 AM