linear

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses the Linear MCP server to call tools like list_issues/get_issue/list_comments/get_document/search_documentation, which will ingest outsider-authored free text such as issue/PR/comment/document body text written by other Linear users into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill requires runtime connections to the external Linear MCP endpoints (https://mcp.linear.app/mcp and https://mcp.linear.app/sse) and explicitly suggests running "npx -y mcp-remote https://mcp.linear.app/sse" (which fetches and executes remote code), making that external service/code a required runtime dependency that can control tool execution.