alternative-agent-frameworks

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly shows agents ingesting external web/HTTP sources (e.g., CrewDoclingSource(file_paths=["https://example.com/docs"]) and MCPServerHTTP / MCPServerSSE / mcps URL examples in the CrewAI and MCP examples), meaning the agents are expected to fetch and read untrusted third‑party content as part of their workflow.