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 fetching and interpreting public web content (e.g., SKILL.md "External References" links, Tools Reference listing "web/fetch"/MCP tools, integrations/microsoft-docs.instructions.md's mandated use of MCP search/fetch, and agent-guide examples like "Fetch https://example.com/docs and analyze"), so untrusted third‑party pages can be ingested and materially influence tool choices and agent actions.