webex-voice-interface
Warn
Audited by Snyk on Jul 30, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a runtime path where an outsider posts a voice clip/transcript into a WebEx space, OpenClaw transcribes it, and NetClaw “treat[s] the transcribed voice message identically to a typed text message,” meaning arbitrary user-authored text is ingested for processing.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata