unitree-robot
Warn
Audited by Snyk on Mar 4, 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 explicitly accepts and executes natural-language commands forwarded from IM platforms (README: "The OpenClaw main agent receives commands from IM (WeChat, WhatsApp, etc.) and forwards them to this skill") and skill.execute() parses and acts on those user-provided messages, so untrusted third-party user content can directly influence robot actions.
Audit Metadata