managed-model-endpoints
Warn
Audited by Socket on Aug 1, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: The skill’s purpose and capabilities mostly align for managed model serving, and it uses documented Docker/NVIDIA patterns rather than obvious malware. However, it executes lifecycle shell scripts, pulls and runs unpinned runbook-defined container images, and forwards credentials to registries/containers or arbitrary remote HTTPS endpoints whose provenance is not verifiable from this skill alone.
Confidence: 84%Severity: 64%
Audit Metadata