use-mcp

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow treats MCP server definitions, tool descriptions, resource contents, and tool results as untrusted input and runs mcporter list / mcporter list <server.tool> --schema / mcporter resource ... --output json which can ingest outsider-authored free text delivered via an MCP server the user selects (including projectable instructions in descriptions/resources).