audio-transcribe

Warn

Audited by Snyk on Apr 17, 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 uploads audio to a third‑party ASR (DashScope / qwen3-asr) and explicitly fetches the transcription JSON via requests.get(transcript_url) in scripts/transcribe.py, and SKILL.md states calling agents read the produced .transcript.md for downstream processing — meaning untrusted/user‑provided spoken content and vendor-generated transcripts are ingested and can materially influence agent decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 17, 2026, 09:08 AM
Issues
1