teable-assistant-ops

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., upload-attachment supports a public fileUrl (api-reference/automation.api.md / guides/cli-reference.md) and webhook triggers provide arbitrary request bodies (api-reference/automation.trigger.md) — and those inputs are read and used by import/analyze, automation scripts, and record-creation workflows, so external content can materially influence actions.