ai-voice-cloning

Fail

Audited by Snyk on Aug 6, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.80). These links point to an unfamiliar third-party CLI host (inference.sh) plus a raw GitHub install doc and a private cloud URL on the same domain — all of which could deliver or instruct running remote code, so they warrant caution.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a CLI workflow where the user-supplied JSON fields like "prompt"/"text" are passed to belt app run ... --input, meaning outsider-authored free text can be ingested directly at runtime by the TTS apps.

Issues (2)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Aug 6, 2026, 05:03 AM
Issues
2
Security Audit — snyk — ai-voice-cloning