voice-batch-runner

Warn

Audited by Snyk on May 17, 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's required runtime flow (see scripts/clone_voice_take.mjs and the normalized request in references/tool-contracts.md) accepts a referenceAudioUrl and submits it to the hosted voice-clone endpoint (voice-qwen3-clone), causing the system/hosted provider to fetch and interpret arbitrary external audio URLs (public/user-provided), which can materially influence generation and downstream actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
May 17, 2026, 07:44 AM
Issues
1
Security Audit — snyk — voice-batch-runner