webflow-automation

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references an external MCP server endpoint (https://rube.app/mcp) and official documentation from composio.dev to provide Webflow automation tools. This is a standard configuration for remote toolsets and does not involve the execution of untrusted scripts.
  • [PROMPT_INJECTION]: The skill retrieves content from external Webflow sites (e.g., CMS items, page DOM structure), which presents an indirect prompt injection surface where external data could potentially influence the agent's behavior.
  • Ingestion points: Data is ingested from Webflow via tools such as WEBFLOW_GET_PAGE_DOM, WEBFLOW_GET_COLLECTION_ITEM, and WEBFLOW_LIST_ORDERS as described in SKILL.md.
  • Boundary markers: No specific delimiters or boundary markers are mentioned to differentiate user data from system instructions.
  • Capability inventory: The skill possesses write capabilities including site publishing (WEBFLOW_PUBLISH_SITE) and CMS modification (WEBFLOW_CREATE_COLLECTION_ITEM, WEBFLOW_DELETE_COLLECTION_ITEM) as listed in SKILL.md.
  • Sanitization: There are no instructions for the agent to sanitize or validate content retrieved from the external site before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:25 PM
Security Audit — agent-trust-hub — webflow-automation