İçeriğe geç
Bilgi ve Teknoloji Uygulamada aç

Yapay Zekâ Önem 61/100

When LLM Gateways Go Wrong: Findings from LiteLLM

Check Point Research ·

TL;DR; Our security assessment of LiteLLM (v1.77.7), a widely used open-source LLM gateway, uncovered multiple high-impact vulnerabilities (tracked as CVE-2026-35029, CVE-2026-59823) which have been resolved as of LiteLLM version 1.83.9. The most significant issues stemmed from a missing authorization check on the /config/update endpoint, which allowed any authenticated user (including low-privileged accounts) to modify the proxy’s runtime configuration. This single flaw enabled arbitrary file read, administrative account takeover, and remote code execution via malicious Python modules loaded

İlgili CVE kayıtları

Etiketler

  • yapay zekâ güvenliği
  • uzaktan kod çalıştırma

Kaynakta oku Uygulamada aç