cms-collection-setup
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious behavior or security risks were identified. The skill follows best practices for tool execution and data management.
- [PROMPT_INJECTION]: The skill processes user-supplied data for CMS definitions which represents an indirect prompt injection surface. 1. Ingestion points: User-provided display names, singular names, and field definitions (SKILL.md, Phase 2). 2. Boundary markers: The process includes a mandatory preview and explicit user approval in Phase 4. 3. Capability inventory: Use of the data_cms_tool to create collections and fields. 4. Sanitization: The skill includes validation steps for field types and plan limits in Phase 3.
- [DATA_EXPOSURE]: The skill is designed to interact with the Webflow API via MCP tools and does not attempt to access sensitive local system files, environment variables, or other credentials.
Audit Metadata