qveris

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow uses MCP discover/inspect/call, and those MCP tool results can include outsider-authored free text (e.g., scraped public web content or other users’ messages) that the agent then ingests into its LLM context during capability discovery/inspection/calling.