voice-processing

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). The skill routinely fetches and processes community-contributed voices and their metadata from the ElevenLabs Voice Library via the API (e.g., scripts/list-voices.sh, examples/voice-library/* calling GET /v1/voices and related endpoints), which are user-generated/untrusted third‑party content that the agent reads and interprets as part of its workflows.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 02:06 AM