airtable

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly reads and acts on user-generated Airtable content via the Airtable API (e.g., records.py list/query/get and comments, and webhooks.py payloads/get), and those external record/comment/webhook payloads are parsed and used in workflows that can trigger updates or other actions, so untrusted third‑party content could carry instructions that influence agent behavior.