characteristic-voice

Warn

Audited by Snyk on Mar 3, 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 SKILL.md "Using a Character's Voice" section explicitly instructs fetching public YouTube videos and downloading/reading subtitles (via yt-dlp) to determine timestamps and supply reference audio to the TTS backend, which ingests untrusted, user-generated third-party content that can influence processing and tool behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 06:25 PM