elevenlabs

Warn

Audited by Snyk on Feb 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). This skill explicitly ingests and processes arbitrary public URLs and user-generated media (e.g., "URL Sources: YouTube, X (Twitter), TikTok, Vimeo, Direct URLs" in references/dubbing.md and the knowledge-base create_from_url usage in references/voice-agents.md), meaning the agent will fetch untrusted third‑party content and use its transcripts/content to drive dubbing/knowledge-base/agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 11:20 AM