gemini-antigravity
Warn
Audited by Socket on Jul 9, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill's main capability matches its stated purpose and official Google Antigravity documentation, but its execution path is only partially verifiable because the CLI wrapper and x402.wtf registry are not clearly Google-operated. The biggest risk is credential forwarding: private repo/API tokens are injected into a remote managed sandbox, and the skill can also load additional SKILL.md instructions, expanding the trust boundary.
Confidence: 87%Severity: 64%
Audit Metadata