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