CVE-2026-12770: Improper Authorization in BerriAI litellm
CVE-2026-12770 is a medium severity vulnerability in BerriAI litellm versions 1.63.0 and 1.63.1. It involves improper authorization in an unknown function within the Admin Key Handler component, specifically in the file litellm/proxy/management_endpoints/key_management_endpoints.py. The vulnerability can be exploited remotely without user interaction. Although the exploit has been publicly disclosed, there is no confirmed patch or official remediation available at this time.
AI Analysis
Technical Summary
This vulnerability affects BerriAI litellm up to versions 1.63.0 and 1.63.1. It is caused by improper authorization in an unspecified function of the Admin Key Handler component, allowing remote attackers to potentially perform unauthorized actions. The issue resides in the key_management_endpoints.py file. The vulnerability has a CVSS 4.0 base score of 5.3, indicating medium severity. The vendor was notified early, but no official fix or patch has been published yet. Exploit details have been publicly disclosed, but no known active exploitation in the wild is reported.
Potential Impact
The improper authorization flaw allows remote attackers to bypass intended access controls within the Admin Key Handler component, potentially leading to unauthorized administrative actions. This could compromise key management functions, affecting the security posture of the affected system. The medium CVSS score reflects a moderate risk due to the ease of remote exploitation without user interaction but limited impact scope as per available data.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no official fix or patch has been published, users should monitor vendor communications for updates. Until a fix is available, restrict access to the affected management endpoints and apply network-level controls to limit exposure. Avoid exposing the vulnerable component to untrusted networks where possible.
CVE-2026-12770: Improper Authorization in BerriAI litellm
Description
CVE-2026-12770 is a medium severity vulnerability in BerriAI litellm versions 1.63.0 and 1.63.1. It involves improper authorization in an unknown function within the Admin Key Handler component, specifically in the file litellm/proxy/management_endpoints/key_management_endpoints.py. The vulnerability can be exploited remotely without user interaction. Although the exploit has been publicly disclosed, there is no confirmed patch or official remediation available at this time.
CVSS v4.0
Score 5.3medium
Affected software
cpe:2.3:a:litellm:litellm:*:*:*:*:*:*:*:*Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
This vulnerability affects BerriAI litellm up to versions 1.63.0 and 1.63.1. It is caused by improper authorization in an unspecified function of the Admin Key Handler component, allowing remote attackers to potentially perform unauthorized actions. The issue resides in the key_management_endpoints.py file. The vulnerability has a CVSS 4.0 base score of 5.3, indicating medium severity. The vendor was notified early, but no official fix or patch has been published yet. Exploit details have been publicly disclosed, but no known active exploitation in the wild is reported.
Potential Impact
The improper authorization flaw allows remote attackers to bypass intended access controls within the Admin Key Handler component, potentially leading to unauthorized administrative actions. This could compromise key management functions, affecting the security posture of the affected system. The medium CVSS score reflects a moderate risk due to the ease of remote exploitation without user interaction but limited impact scope as per available data.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Since no official fix or patch has been published, users should monitor vendor communications for updates. Until a fix is available, restrict access to the affected management endpoints and apply network-level controls to limit exposure. Avoid exposing the vulnerable component to untrusted networks where possible.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulDB
- Date Reserved
- 2026-06-20T09:26:17.378Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a3732a99c760d8add0c8b0e
Added to database: 06/21/2026, 00:39:05 UTC
Last enriched: 06/21/2026, 00:52:43 UTC
Last updated: 06/21/2026, 02:34:53 UTC
Views: 6
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.