jimeng-image
Warn
Audited by Snyk on May 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill accepts arbitrary http/https reference-image URLs (see README/SKILL.md and scripts/jimeng_image.py collect_reference_images/download_url, plus batch/workflow scripts that pass --image values) and downloads/ingests those external images as part of its generation workflow, which could allow untrusted, user-controlled content to influence model outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata