webflow-mcp:interactions
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a technical interface for Webflow interaction management with clear boundaries and user confirmation steps. It relies on official MCP tools and maintains a clear separation between agent instructions and site data.
- [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface (reading site interactions) but incorporates strong mitigation strategies. It mandates following a strict schema provided by the
guideaction, uses deterministic validation at the API boundary, and requires explicit user confirmation for all create, update, and delete actions. These measures effectively manage the risks associated with processing untrusted site content. - [EXTERNAL_DOWNLOADS]: All external links and installation references point to official Webflow GitHub repositories and verified vendor endpoints. These are within the trusted scope for a skill authored by the vendor.
Audit Metadata