Transcription Automation
Warn
Audited by Snyk on Jun 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime transcription pipeline ingests audio/video content from outsider-provided sources (e.g., Zoom recordings, YouTube videos, RSS feed audio, or arbitrary URLs like
https://example.com/meeting.mp3), and the resulting transcribed text (free-form speech) is then fed into the agent/LLM context for post-processing/summary/notes.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata