video-perception
Warn
Audited by Snyk on Aug 26, 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). In the video-perception skill workflow, runtime LLM-readable free text comes from user-provided video audio (transcription) extracted via
video_analyze/video_watch/video_detail, which can include outsider-authored spoken content and thus indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata