feathery
Warn
Audited by Socket on Apr 28, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill is mostly coherent with its stated Feathery-integration purpose and uses an official npm-distributed Membrane CLI, so it does not look malicious. However, it routes authentication and Feathery operations through Membrane as a third-party intermediary instead of Feathery's official API, and grants the agent broad remote read/write/delete capabilities. That makes it a medium-risk integration skill rather than benign low-risk tooling.
Confidence: 84%Severity: 58%
Audit Metadata