deepl
Warn
Audited by Socket on Sep 15, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill is not overt malware, but its actual footprint is broader than a normal DeepL integration. It installs a third-party CLI, forwards authentication and API activity through Membrane-operated infrastructure instead of DeepL directly, and uses an unpinned global package install. This is a coherent integration pattern for Membrane, but not proportionate to a plain 'DeepL' skill without clearly foregrounding the intermediary trust boundary.
Confidence: 87%Severity: 63%
Audit Metadata