lark-event
Warn
Audited by Snyk on Apr 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's subscribe command (references/lark-event-subscribe.md / "Agent Pipeline Examples") connects via WebSocket to receive im.message.receive_v1 events and explicitly parses message "content" and pipes it into downstream agents (e.g., Claude) and automatic reply APIs, so untrusted user-generated messages are ingested and can influence subsequent tool actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata