xiaohu-wechat-cover
Warn
Audited by Socket on Mar 26, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the core image-generation purpose is coherent, but the skill’s data flow is not. It requires reading a raw API key from local config and forwarding prompts plus credentials to an arbitrary third-party Gemini-compatible gateway rather than an official Gemini endpoint, and it also auto-edits the article file by default. Main risk is credential/data routing through an intermediary, not confirmed malware.
Confidence: 90%Severity: 78%
Audit Metadata