MediumNewsLLM-specific
When LLM Gateways Go Wrong: Findings from LiteLLM
- Published
- Record updated
Summary
Check Point Research assessed LiteLLM (v1.77.7), an open-source LLM gateway, and found multiple high-impact vulnerabilities, tracked as CVE-2026-35029 and CVE-2026-59823. The most significant flaw is a missing authorization check on the /config/update endpoint, which lets any authenticated user, including low-privileged accounts, modify the configuration.
Mitigation
Resolved as of LiteLLM version 1.83.9.
Related items
- HighCVE-2026-109403: conductor-oss conductor server-side request forgery in agent card fetchingSimilar attack · NVD/CVE Database
- InfoExploring Backdoor Vulnerabilities and Fairness Challenges in Generative Models: A SurveySimilar attack · ACM Digital Library (TOPS, DTRAP, CSUR)
- LowSmall AI Models Could Soon Self-Replicate on IoT Devices, Anthropic WarnsSimilar attack · SecurityWeek
- MediumCVE-2026-108940: Mistral.rs path traversal through calibration_apply save_cimatrix argumentSimilar attack · NVD/CVE Database
- MediumCVE-2026-108939: mistral.rs server-side request forgery in is_global_ip validationSimilar attack · NVD/CVE Database