api-server-mcp

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

• Third-party content exposure detected (high risk: 0.70). The required workflow includes an outsider-controlled runtime URL path (POST /extract-url) that fetches arbitrary web content and (by the description) feeds the extracted bytes/text into the extraction pipeline/returned ToolResult for MCP/LLM use, which creates an indirect prompt-injection risk from public web free text.