create-cowork-plugin

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs creating and using MCP servers with remote HTTP/SSE URLs (see ".mcp.json" examples in SKILL.md and references, e.g., entries for "github", "asana", "linear") and includes agents/hooks that read external ticket/issue data (e.g., the ticket-analyzer agent: "Read all ticket descriptions") — meaning the agent will fetch and interpret untrusted, user-generated third‑party content that can drive decisions and tool use.