happy-horse-video-reference-to-video
Warn
Audited by Snyk on Aug 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). Source: user-provided runtime arguments (
--prompt/--system) are incorporated into themessagespayload and sent to the AI Hive API viaAiHiveClient.chat_text(...)/cmd_video(...)→client.generate_video(...)(scripts/videogen.py, lines 669-687 and 510-530), so outsider free text can directly influence what the service receives.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata