personize-no-code-pipelines

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests untrusted third-party content — e.g., reading arbitrary Google Sheets URLs in templates/gsheets-to-personize.json, accepting external webhook payloads in templates/webhook-to-personize.json, and instructing the agent to fetch public n8n/docs and community templates (reference/n8n-reference.md) — which the agent must parse and which can materially change mapping, prompts, and workflow actions.