n8n

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

• Third-party content exposure detected (high risk: 1.00). The skill's documentation and workflows explicitly instruct agents to fetch and use external web and API content (e.g., "HTTP Request Tool" and web-search/SerpAPI/Wikipedia tools, RAG workflows and the AI Agent instructions in SKILL.md and references/advanced.md), so untrusted public webpages and search results are ingested and used to drive agent decisions and tool calls.