google-gemini
Warn
Audited by Socket on Mar 14, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill's core function is plausible, and the CLI install source is consistent with the publisher, but the actual data flow is not a direct Google Gemini integration. All requests and auth are funneled through Membrane as an intermediary proxy, which is broader trust than the skill title implies and creates meaningful third-party exposure of prompts and connection data.
Confidence: 89%Severity: 61%
Audit Metadata