n8n-photo-report

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow clearly ingests user-provided third‑party photos via the "Photo Webhook" and a Dropbox watch node, sends those untrusted images to Claude Vision for analysis, and then uses the model's parsed output to categorize, store, and drive reporting actions—so external/user-generated content can materially influence agent behavior and enable indirect prompt injection.