site-audit

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes several Webflow MCP tools including data_sites_tool, data_pages_tool, and data_cms_tool. These calls are used to perform structural audits and content inventories of Webflow sites, which is consistent with the skill's primary purpose.
  • [PROMPT_INJECTION]: The skill processes untrusted data from external Webflow sites, creating a surface for indirect prompt injection.
  • Ingestion points: Site metadata, page slugs, and CMS collection items retrieved via MCP tools.
  • Boundary markers: No explicit markers are defined to distinguish content from instructions.
  • Capability inventory: Read-only access to site structure and content with output formatting to Markdown, JSON, and CSV.
  • Sanitization: None specified for the content retrieved from the Webflow API.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 07:37 AM