wonderchat
Warn
Audited by Socket on Apr 2, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill is mostly coherent as a Membrane-hosted Wonderchat integration and uses a legitimate npm-published CLI, but it adds a third-party proxy/control plane for all API access and includes a mismatched official-docs reference. This is not confirmed malicious, yet the intermediary data flow and documentation inconsistency make the skill medium risk rather than clearly benign.
Confidence: 82%Severity: 58%
Audit Metadata