qwen-image-2-pro
Warn
Audited by Socket on Mar 17, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill’s core purpose is coherent, but it relies on transitive skill installation, broad `infsh` CLI permissions, and credential/data routing through inference.sh rather than a direct official Alibaba integration. This looks more like a platform wrapper than a narrowly scoped model skill; concerning from a trust/scope standpoint, but not clearly malicious.
Confidence: 84%Severity: 58%
Audit Metadata