MeiGen Visual Creative Expert
Warn
Audited by Snyk on Feb 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill explicitly ingests public gallery entries and arbitrary public URLs as reference images (see the "search_gallery" → "get_inspiration" workflow and "referenceImages takes an array of public URLs" in SKILL.md), so untrusted/user-generated content can be read and used to influence prompt generation and image-generation decisions.
Audit Metadata