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's instructions explicitly require using web/MCP fetch tools and external URLs (see .github/instructions/integrations/microsoft-docs.instructions.md, agent-guide.md and the External References list) so the agent will retrieve and act on public third‑party webpages/documents that can influence tool use and decisions.