lark-event

Warn

Audited by Snyk on Mar 28, 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 subscribes to Lark events via a WebSocket long connection (lark-cli event +subscribe in references/lark-event-subscribe.md) and ingests user-generated IM/event payloads (e.g., im.message.receive_v1) which the agent is shown parsing and feeding into downstream tools (e.g., generating replies with Claude), so untrusted third-party content can materially influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 28, 2026, 02:44 AM
Issues
1