gitnexus
Warn
Audited by Socket on Apr 7, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core goal—repo indexing and editor/MCP integration—is plausible, but the actual footprint is broader: global install, multi-editor config rewrites, hook installation, generated skills, and autonomous execution without user confirmation. The biggest concern is provenance mismatch between the skill metadata and the observed npm package publisher/version, plus transitive installation of additional skills into agent environments. No explicit credential theft or exfiltration is shown, so this is not confirmed malware, but it is a medium-high risk skill.
Confidence: 84%Severity: 76%
Audit Metadata