jentic-api-improve
Warn
Audited by Socket on Sep 22, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the core capability is coherent with improving OpenAPI specs and the main tools appear to be official Jentic/registry-distributed dependencies, so this is not confirmed malware. However, the skill materially increases trust requirements by promoting bypassPermissions, broad Bash pre-approvals, autonomous subagent execution, unpinned npx installs, Docker pulls, and forwarding API/provider credentials to external CLIs and services.
Confidence: 88%Severity: 58%
Audit Metadata