seedream-5-lite-livestream-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). The runtime workflow ingests outsider-provided free text via the
--promptargument incmd_image/client.generate_image, which is sent to the external OpenAPI endpoint as the model prompt (prompt: prompt).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata