antigravity-manager
Warn
Audited by Socket on Mar 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s stated purpose matches its behavior, but that behavior is inherently high-risk: it forwards sensitive web session tokens into third-party proxy software, exposes model traffic through an interception layer, and uses remote script installers from a repo owner not clearly tied to the skill publisher. Plaintext/log-based credential recovery further raises risk.
Confidence: 84%Severity: 82%
Audit Metadata