together-audio
Warn
Audited by Snyk on Mar 30, 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 supports ingesting audio from public HTTP/HTTPS URLs (see references/stt-models.md "file = ... URL" and SKILL.md "Transcribe uploaded audio files or URLs"), so arbitrary third‑party audio content can be read and influence transcription-driven agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata