safegraph
Warn
Audited by Socket on Apr 2, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill is mostly coherent with its stated SafeGraph integration purpose and uses an official npm-distributed Membrane CLI, so it does not look malicious. However, it routes authentication and API traffic through Membrane instead of directly to SafeGraph, creating a meaningful third-party credential and data-flow trust dependency; combined with unpinned `npx ...@latest`, this makes it medium risk rather than benign.
Confidence: 87%Severity: 52%
Audit Metadata