agentic-workflow-guide

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs agents to fetch and summarize open-web content (e.g., "Fetch https://example.com/docs and analyze" in references/agent-guide.md and the External References list in assets/workspace-templates/instructions/integrations/external-references.instructions.md) using tools like web/fetch and MCP, so it will ingest untrusted public third-party content as part of its workflow.