wordpress-mcp-dev

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's MCP server tools explicitly call arbitrary WordPress sites via the WordPressClient (e.g., getPages, getSiteContext in references/full-guide.md and the src examples) and return that site content for the AI to read and act on, meaning untrusted third-party (user/site-provided) content can be ingested and influence tool selection and subsequent actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The MCP server tools call the configured WordPress REST API at runtime (e.g., https://example.com/wp-json/wp/v2/pages or other endpoints under https:///wp-json), and the fetched page/site data is returned in tool responses and injected into the model context—meaning remote content can directly influence agent prompts and behavior.