happyhorse
Warn
Audited by Socket on Sep 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The stated video-generation purpose is coherent, but the skill's main footprint is transitive installation of other skills and mutable external install guidance rather than a self-contained Alibaba/inference.sh integration. No direct credential theft or exfiltration is shown here, but the trust chain and cross-org dependency pattern make it medium-high risk.
Confidence: 87%Severity: 72%
Audit Metadata