LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key

MITRE NVD CVE.ORG JSON API

Summary

CVECVE-2026-114612
StatePUBLISHED
AssignerGitHub_M
Source PriorityCVE Program / NVD first with legacy fallback
Published2026-10-22 19:17:37 UTC
Updated2026-10-22 19:17:37 UTC
DescriptionLiteLLM is a proxy server (AI Gateway) to call LLM APIs in OpenAI (or native) format. From 1.87.0 until 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2, the proxy reuses one cryptographic context for at-rest secrets and session tokens, allowing an authenticated internal user to have crafted metadata containing a forged administrator credential encrypted and returned by the API-key flow. Replaying that ciphertext as a bearer token causes the proxy to trust the forged proxy administrator identity, permitting administrative access and arbitrary commands through the MCP stdio endpoint. Versions 1.87.0 through 1.90.x require EXPERIMENTAL_UI_LOGIN to be enabled, while versions after 1.91.0 are exploitable in the default configuration. This issue was fixed in LiteLLM 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2.

Risk And Classification

Primary CVSS: v3.1 9.9 CRITICAL from [email protected]

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Problem Types: CWE-269 | CWE-345 | CWE-441 | CWE-269 CWE-269: Improper Privilege Management | CWE-345 CWE-345: Insufficient Verification of Data Authenticity | CWE-441 CWE-441: Unintended Proxy or Intermediary ('Confused Deputy')

VersionSourceTypeScoreSeverityVector
3.1[email protected]Secondary9.9CRITICALCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
3.1CNADECLARED9.9CRITICALCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

CVSS v3.1 Breakdown

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Changed
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H

Vendor Declared Affected Products

SourceVendorProductVersionPlatforms
CNA BerriAI Litellm affected >= 1.87.0, < 1.100.4 Not specified
CNA BerriAI Litellm affected >= 1.101.0, < 1.101.3 Not specified
CNA BerriAI Litellm affected >= 1.102.0, < 1.102.2 Not specified
CNA BerriAI Litellm affected >= 1.103.0, < 1.103.1 Not specified
CNA BerriAI Litellm affected >= 1.104.0-rc.1, < 1.104.0-rc.2 Not specified

References

ReferenceSourceLinkTags
github.com/BerriAI/litellm/releases/tag/v1.100.4 [email protected] github.com
github.com/BerriAI/litellm/security/advisories/GHSA-7hp6-4w63-5g45 [email protected] github.com
github.com/BerriAI/litellm/commit/f7cd90f09e9716652b38daec9f0640cdf49d582b [email protected] github.com
github.com/BerriAI/litellm/commit/9161d7f9d6073603ba61ee4aa5e2c0ef5b37a81b [email protected] github.com
github.com/BerriAI/litellm/releases/tag/v1.102.2 [email protected] github.com
github.com/BerriAI/litellm/releases/tag/v1.103.1 [email protected] github.com
github.com/BerriAI/litellm/commit/a80eacacee118fbed54e3d98f239d17a63fac818 [email protected] github.com
github.com/BerriAI/litellm/commit/9fa1a641119dd0d4fe43e93622eae5f482ceb63f [email protected] github.com
github.com/BerriAI/litellm/releases/tag/v1.104.0-rc.2 [email protected] github.com
github.com/BerriAI/litellm/commit/1d5fdc87fed66b49e1df8cf7d708ad93249eb7d0 [email protected] github.com
github.com/BerriAI/litellm/releases/tag/v1.101.3 [email protected] github.com
CVE Program record CVE.ORG www.cve.org canonical
NVD vulnerability detail NVD nvd.nist.gov canonical, analysis

© CVE.report 2026

Use of this information constitutes acceptance for use in an AS IS condition. There are NO warranties, implied or otherwise, with regard to this information or its use. Any use of this information is at the user's risk. It is the responsibility of user to evaluate the accuracy, completeness or usefulness of any information, opinion, advice or other content. EACH USER WILL BE SOLELY RESPONSIBLE FOR ANY consequences of his or her direct or indirect use of this web site. ALL WARRANTIES OF ANY KIND ARE EXPRESSLY DISCLAIMED. This site will NOT BE LIABLE FOR ANY DIRECT, INDIRECT or any other kind of loss.

CVE, CWE, and OVAL are registred trademarks of The MITRE Corporation and the authoritative source of CVE content is MITRE's CVE web site. This site includes MITRE data granted under the following license.

Free CVE JSON API cve.report/api

CVE.report and Source URL Uptime Status status.cve.report