image-generation
Warn
Audited by Socket on Sep 15, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The core behavior matches an image-generation skill, and there is no clear malware or installer abuse. The main risk is data-flow integrity: credentials and reference images are forwarded through an opaque local script, OpenAI-compatible mode allows arbitrary third-party endpoints, and the documented MiniMax host is inconsistent with official docs.
Confidence: 88%Severity: 57%
Audit Metadata