n8n-data-tables

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

• Third-party content exposure detected (high risk: 0.90). The skill's idempotency webhook pattern (references/DEDUP_PATTERNS.md) explicitly ingests arbitrary webhook request bodies/headers and stores/reads responseBody from Data Tables—i.e., untrusted external/user-provided content is read and used to decide responses—so third-party content can indirectly inject instructions.