anthropic
Warn
Audited by Socket on Sep 17, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill is coherent as an Anthropic integration guide, and the install path uses an official npm package rather than an opaque binary. But the actual integration is not direct: authentication, credential refresh, and API requests are routed through Membrane, a third-party intermediary, which creates medium data-flow and trust risk disproportionate to a straightforward Anthropic skill.
Confidence: 87%Severity: 61%
Audit Metadata