typescript-mcp

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

• Third-party content exposure detected (high risk: 0.85). At runtime, the skill’s required HTTP MCP workflow ingests the caller-supplied JSON-RPC request body (including free-form tool arguments) via transport.handleRequest(c.req.raw, c.res.raw, await c.req.json()), so outsider-authored text from any external client can be passed into the MCP server/LLM context.