openclaw-native
Warn
Audited by Snyk on Apr 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts events from an OpenClaw gateway that connects to public channels (Discord, Slack, Telegram) and forwards "channel_message" events to Kit (SKILL.md "OpenClaw → Kit Events" table: channel_message → Status update) and "agent_task_assigned" loads context/pre-loads files and memory sync feeds Kit's tasks/lessons.md, so untrusted, user-generated third‑party content is read and can influence agent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata