exact-text-image
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 (medium risk: 0.30). Outsider-authored free text is ingested directly from the CLI argument
--prompt(and optional--system) and sent to the AI Hive runtime viaclient.generate_image(..., prompt=args.prompt, ...), without any need to first select a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata