x-mcp

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

• Third-party content exposure detected (high risk: 0.95). The skill’s runtime reads are performed by the native MCP client calling the outsider-authored X MCP server (https://api.x.com/mcp) and ingesting the returned tweet/user text into the agent context via MCP tool outputs (e.g., search/timeline/get_posts), which are authored by non-operating users.