vhscli
Warn
Audited by Socket on May 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill's media-analysis and generation behavior is broadly aligned with its stated purpose, but the trust model is weak. It mandates unpinned npx execution of a remote CLI, routes local files and prompts to server-side backends, and provides limited provenance or endpoint verification. This looks more like a high-trust third-party integration than overt malware, but the install and data-flow risks are non-trivial.
Confidence: 80%Severity: 63%
Audit Metadata