speech-to-text
Warn
Audited by Snyk on Aug 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a required runtime workflow that transcribes user-supplied media URLs via the inference.sh CLI (
belt app run ... --inputwithaudio_url/video_url), so the workflow ingests outsider-provided content (audio/video) as transcribed free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata