skills/zoom/skills/voice-agent/Snyk

voice-agent

Warn

Audited by Snyk on Oct 26, 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). The skill implements a real-time voice agent WebSocket interface that transcribes user speech into text processed by an LLM turn, which constitutes ingestion of outsider-authored free text from microphone audio streams.

Issues (1)

W011

MEDIUM

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

Audit Metadata

Risk Level

MEDIUM

Analyzed

Oct 26, 2026, 07:08 AM

Issues

1