link-checker

Pass

Audited by Gen Agent Trust Hub on Apr 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill uses official Webflow MCP tools for all operations, which scopes activities to the authorized Webflow environment.
  • [SAFE]: The process requires explicit user confirmation (Phase 4) for every proposed modification, preventing autonomous unauthorized changes.
  • [DATA_EXFILTRATION]: The skill performs network requests to validate the accessibility of external URLs. This is the intended functional behavior of a link checker and does not represent an exfiltration of sensitive data.
  • [COMMAND_EXECUTION]: Modifies site content and CMS items through the Webflow API. These operations require a Designer connection and are restricted to the site context provided by the user.
  • [PROMPT_INJECTION]: The skill processes untrusted content from the user's website, creating a surface for indirect prompt injection.
  • Ingestion points: Page content via data_pages_tool and CMS items via data_cms_tool.
  • Boundary markers: None specified in the instructions.
  • Capability inventory: Static page and CMS update tools.
  • Sanitization: Logic focuses on parsing HTML link tags.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 8, 2026, 07:37 AM