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
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata