All vulnerabilities
CVE-2026-114612GHSA-7hp6-4w63-5g45

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

BerriAI litellm
CVSS
9.9Critical
ExploitationNo known exploitationNot in CISA KEV, which does not prove it is unexploitedCISA KEV
Exploit odds (EPSS)0.24%Chance of exploitation activity in the next 30 days, higher than 13% of CVEs. Scored 23 Oct 2026FIRST EPSS
Fixed in1.100.4Also 1.101.3, 1.102.2 and 2 moreGitHub
Published22 Oct 2026Updated 22 Oct 2026CVE List

What fixes it

A fixed version on one release line is not the upgrade target for every line. Check your exact version and any vendor backports.

Description

LiteLLM 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.

Text from CVE List

Affected versions 10

  • litellmaffected: >= 1.87.0, < 1.100.4CVE List
  • litellmaffected: >= 1.101.0, < 1.101.3CVE List
  • litellmaffected: >= 1.102.0, < 1.102.2CVE List
  • litellmaffected: >= 1.103.0, < 1.103.1CVE List
  • litellmaffected: >= 1.104.0-rc.1, < 1.104.0-rc.2CVE List
  • litellm, pip>= 1.91.0, < 1.100.4GitHub
  • litellm, pip>= 1.101.0, < 1.101.3GitHub
  • litellm, pip>= 1.102.0, < 1.102.2GitHub
  • litellm, pip>= 1.103.0, <1.103.1GitHub
  • litellm, pip>= 1.104.0rc1, < 1.104.0rc2GitHub

References 11