webflow-automation

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to configure a remote MCP server located at https://rube.app/mcp. This server defines the toolset available to the agent, creating a dependency on an external service provider for core functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses the capability to ingest and process data from external sources, making it susceptible to indirect prompt injection attacks. * Ingestion points: Untrusted data enters the agent context through tools like WEBFLOW_GET_PAGE_DOM, WEBFLOW_LIST_COLLECTION_ITEMS, WEBFLOW_GET_COLLECTION_ITEM, and WEBFLOW_GET_ORDER as described in SKILL.md. * Boundary markers: The instructions do not define delimiters or specific warnings to ignore instructions embedded within the retrieved Webflow content. * Capability inventory: The skill includes powerful capabilities such as WEBFLOW_PUBLISH_SITE, WEBFLOW_DELETE_COLLECTION_ITEM, and WEBFLOW_UPLOAD_ASSET across the Webflow toolkit. * Sanitization: There is no mention of sanitization, validation, or filtering of the content retrieved from Webflow before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 05:00 PM
Security Audit — agent-trust-hub — webflow-automation