elevenlabs-stt

Warn

Audited by Snyk on Mar 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: 0.80). The skill's required workflow (scripts/transcribe.sh and SKILL.md) sends arbitrary user-provided audio to the ElevenLabs Speech-to-Text API and returns the API/transcribed text (JSON or plain text) for the agent to read, which is untrusted user-generated content that could contain instructions influencing subsequent actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 21, 2026, 01:00 PM
Issues
1