- Published
- Source
- Check Point Research
- Filed under
- Malware & exploits, AI for defence
- Vulnerabilities
- 2 CVEs
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…
Using AI safely
- Know which AI tools your organisation uses, and what data goes into them.
- Treat AI agents like any other identity: least privilege, logging and a named owner.
- Test AI features for prompt injection and data leakage before customers reach them.
More helpNCSC: guidelines for secure AI system development (opens in a new tab)
The vulnerabilities in this story
CVE-2026-35029 in the NVD (opens in a new tab)
- CVSS8.8High
- CISA KEVNot listedno confirmed exploitation on CISA’s list (yet)
CVE-2026-59823 in the NVD (opens in a new tab)
- CVSS5.3Medium
- CISA KEVNot listedno confirmed exploitation on CISA’s list (yet)
Exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog (CC0). Exploit prediction: EPSS by FIRST. This product uses the NVD API but is not endorsed or certified by the NVD.
MyCyberWay training
AI security · in both programmes
AI is part of the attack surface now. Learn to watch it.
Blue Team Analyst covers Security Copilot in triage and monitoring the AI itself: inherited permissions, prompt injection and Purview DSPM for AI. Blue Team Engineer secures the deployment: Copilot pre-flight hardening, agent identity and tool allow-lists.
- Security Copilot in triage
- Prompt injection and DSPM for AI
- Agent identity and allow-lists
Headlines and short summaries only, except where a public body publishes under an open licence. Every story links to its publisher, who owns it. MyCyberWay does not edit or endorse third-party reporting.
