create-cowork-plugin

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Phase 2 & Phase 3) explicitly asks about and mandates adding MCP server integrations and tool exposures, and Phase 4 instructs creating a .mcp.json with remote URLs (see MCP Servers section and the example plugins like engineering-workflow/ticket-analyzer that read tickets via .mcp.json), which means the agent will ingest and act on untrusted, user-generated content from third-party APIs/servers during normal operation.