CVE-2026-114612: CWE-269: Improper Privilege Management in BerriAI litellm
Description
LiteLLM versions from 1.87.0 up to but not including 1.100.4, and certain subsequent minor versions, contain an improper privilege management vulnerability. The proxy server reuses a cryptographic context for secrets and session tokens, enabling an authenticated internal user to forge administrator credentials. This allows escalation to administrative access and execution of arbitrary commands via the MCP stdio endpoint. Early vulnerable versions require an experimental login feature enabled, while later versions are exploitable by default. The issue is fixed in versions 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2.
CVSS v3.1
Score 9.9critical
Affected software
BerriAI
litellm
pkg:github/berriai/litellmRun 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
CVE-2026-114612 describes an improper privilege management vulnerability in BerriAI's LiteLLM proxy server. From versions 1.87.0 through 1.100.4 (exclusive) and certain subsequent minor versions, the proxy reuses a single cryptographic context for both at-rest secrets and session tokens. This flaw allows an authenticated internal user to craft metadata containing a forged administrator credential encrypted by the API-key flow. Replaying this forged ciphertext as a bearer token causes the proxy to trust the forged administrator identity, granting administrative access and the ability to execute arbitrary commands through the MCP stdio endpoint. Versions 1.87.0 through 1.90.x require the EXPERIMENTAL_UI_LOGIN feature enabled for exploitation, whereas versions after 1.91.0 are vulnerable in default configurations. The vulnerability is addressed in versions 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2.
Potential Impact
Successful exploitation allows an authenticated internal user to escalate privileges to administrator level, enabling arbitrary command execution on the proxy server. This compromises confidentiality, integrity, and availability of the affected system, as indicated by the CVSS score of 9.9 (critical).
Mitigation Recommendations
This vulnerability has been fixed in LiteLLM versions 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2. Users should upgrade to one of these versions to remediate the issue. No vendor advisory content contradicts this; thus, upgrading is the recommended action.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-10-21T20:34:25.599Z
- Cvss Version
- 3.1
- State
- PUBLISHED
Threat ID: 6ada56624d27ba8daa709b02
Added to database: 10/22/2026, 18:30:58 UTC
Last enriched: 10/22/2026, 18:45:20 UTC
Last updated: 10/22/2026, 18:46:12 UTC
Views: 5
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.