n8n-v2

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

• Third-party content exposure detected (high risk: 0.90). The skill’s workflow examples and node patterns explicitly fetch and ingest public third‑party content (e.g., HTTP Request nodes to NewsAPI: https://newsapi.org/v2/everything in assets/examples/news-aggregation-workflow.json, Hacker News API in assets/examples/multi-source-deduplication-workflow.json, RSS feeds like blog.n8n.io, and generic HTTP Request nodes that accept arbitrary URLs) and then read/transform that untrusted/user-generated content (used directly in Set/Code nodes and to build AI prompts in assets/examples/content-generation-workflow.json), so the agent would consume and interpret external untrusted content as part of its workflow.