mandrill
Warn
Audited by Socket on Apr 3, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS. The skill's overall capability fits a Mandrill integration, and its CLI comes from an official npm package tied to the same vendor, so this is not outright malicious. But the documentation has a clear service mismatch, and all API access is funneled through Membrane's intermediary proxy rather than direct Mandrill endpoints, creating moderate trust and data-flow risk disproportionate to a simple API guide.
Confidence: 87%Severity: 57%
Audit Metadata