Skip to content
High-Risk Vulnerabilities Discovered in LiteLLM Gateway

High-Risk Vulnerabilities Discovered in LiteLLM Gateway

First seen 13 Oct 2026, 19:58 UTC • •
API

Article Content

Browse articles
ThreatCluster AI
ThreatCluster •October 13, 2026 at 21:03 UTC

Check Point Research identified two significant vulnerabilities in LiteLLM, an open-source LLM gateway, tracked as CVE-2026-35029 and CVE-2026-59823. CVE-2026-35029 allows low-privileged users to perform administrative actions, potentially leading to full system takeover. CVE-2026-59823 enables attackers to redirect requests to their own servers, exposing sensitive API keys. With 97 million downloads monthly, LiteLLM is widely used across enterprises and startups, making these vulnerabilities particularly impactful. Both issues were patched in LiteLLM version 1.83.9, and organizations are urged to update immediately. The vulnerabilities highlight the need for robust access control and input validation in AI infrastructure tools.

Start a free Starter trial for enhanced analysis

Ask AI about this cluster

Updated just now How this analysis works

Timeline

2026-04-06
CVE-2026-35029 published
Access control vulnerability disclosed, allowing low-privileged users administrative access.
Research.Checkpoint
2026-09-16
CVE-2026-59823 published
Server-side request forgery vulnerability disclosed, enabling request redirection.
Research.Checkpoint
2026-10-13
Patch released for LiteLLM
LiteLLM version 1.83.9 released to address both vulnerabilities; users urged to update.
Blog.Checkpoint

More articles in this cluster (4)

Following this threat?

Track CVE-2026-35029 in your own feed — you're alerted when they show up in new reporting, leak sites or exploitation.

Free account · no card needed

Extracted Entities (10)

1 / 3

Common questions

What versions of LiteLLM are affected?
LiteLLM versions prior to 1.83.9 are affected by the vulnerabilities.
How urgent is the patch?
Organizations should update to version 1.83.9 immediately to mitigate the risks.
What are the main risks associated with these vulnerabilities?
The main risks include unauthorized administrative access and potential exposure of sensitive API keys.