mcporter

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

• Third-party content exposure detected (medium risk: 0.65). mcporter supports runtime discovery/connection to arbitrary MCP servers via --http-url and ad-hoc --stdio commands, and then calls their tools; any tool responses or server-provided text (e.g., scraped/remote content) can be ingested into the agent’s LLM context, creating an outsider free-text injection path.