webflow-mcp:safe-publish

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to call Webflow MCP APIs (data_pages_tool, data_cms_tool, data_sites_tool) and to use WebFetch to retrieve site pages, CMS items and published URLs—i.e., arbitrary user-generated/public Webflow site content—which the agent must read and act on for change detection, validation and publish decisions, creating a clear avenue for indirect prompt injection.