When LLM Gateways Go Wrong: Findings from LiteLLM
2026-10-13T20:52:17Z•c69258ab95c50af98fcc54b8eb0bbf77ef31b42b1f0fbe0536b9e4e9a3450950
CVE-2026-35029CVE-2026-59823AI securityCVELLM gatewayLiteLLMauthorization bypassconfiguration tamperingcyber threat intelligencedata leakagemalwareprivilege escalationprompt injection
What happened
Check Point Research reports multiple high-impact LiteLLM vulnerabilities in version 1.77.7, including missing authorization on the /config/update endpoint that allowed any authenticated, potentially low-privileged user to modify gateway configuration. The issues are tracked as CVE-2026-35029 and CVE-2026-59823 and were fixed in LiteLLM 1.83.9. The feed also covers AI attack techniques, data leakage, malware, campaigns, and recent breaches.
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- checkpoint_research
- Record identifier
- c69258ab95c50af98fcc54b8eb0bbf77ef31b42b1f0fbe0536b9e4e9a3450950
- Enrichment time
- 2026-10-13T20:52:17Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.