elevenlabs-transcribe
Warn
Audited by Snyk on Apr 25, 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 explicitly supports realtime streaming from arbitrary public URLs (see "Realtime Streaming" / "--url https://npr-ice.streamguys1.com/live.mp3"), so the agent can fetch and transcribe untrusted third‑party audio from the open web which the agent is expected to read and could influence its subsequent behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata