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
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 02:58 AM
Issues
1