webflow-mcp:site-audit
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Webflow sites (CMS items, page descriptions) via
data_cms_toolanddata_pages_tool. This data is then used to generate scores and insights. There is a potential attack surface for indirect prompt injection if the audited content contains instructions designed to manipulate the agent's output. - Ingestion points: Site content retrieved via
data_pages_toolanddata_cms_tool. - Boundary markers: None. No specific delimiters or "ignore" instructions are provided for processed site data.
- Capability inventory: File writing (for exports), data analysis, and report generation.
- Sanitization: None specified for the content retrieved from the API.
- [SAFE]: The skill strictly adheres to using vendor-authorized Webflow MCP tools for data retrieval. It does not perform any unauthorized network operations, access sensitive local files, or execute external scripts. The instructions include strict guidelines for tool usage, which acts as a security constraint.
Audit Metadata