NYC

dingtalk-connection

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.85). This skill accepts DingTalk outgoing webhook messages via bridge.py (DingTalk cloud -> webhook) and forwards user-generated DingTalk messages into the agent, so it ingests untrusted third-party content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:38 AM