CVE-2026-114612: LiteLLM: Privilege Escalation to Proxy Admin via Cross-Domain Reuse of the Salt Key

Published Oct 22, 2026
·
Updated

Summary

An authenticated user with internaluser privileges can escalate to proxyadmin and achieve remote code execution. The proxy uses one encryption key for two purposes: sealing secrets at rest and minting session tokens. An attacker exploits this by requesting a new API key with a crafted metadata field containing a forged admin credential as the "secret" value. The proxy encrypts and returns this payload. When this value is then presented as a bearer token, the proxy decrypts it, trusts the forged admin identity, and grants full administrative access, including the ability to execute arbitrary commands via the MCP stdio endpoint.

Affected versions

Versions later than 1.91.0 are exploitable in the default configuration. Versions 1.87.0 through 1.90.x are exploitable only if EXPERIMENTALUILOGIN=true was explicitly set.

Mitigation

Upgrade to a patched version as soon as possible.

If you cannot upgrade immediately, set EXPERIMENTALUILOGIN=false. This disables the vulnerable authentication path but also breaks CLI SSO and Claude Code gateway login.

Impact

An internal user can escalate to proxy admin and execute arbitrary commands on the host.

Discovery Credit: Hoa X. Nguyen (OPSWAT Unit 515)

Other sources

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 EXPERIMENTALUILOGIN 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.

— MITRE

Affected Software

6 affected componentsFixes available
BerriAI LiteLLM>=1.87.0<1.100.4, >=1.101.0<1.101.3, >=1.102.0<1.102.2, >=1.103.0<1.103.1, >=1.104.0<1.104.0-rc.2
pip/litellm>=1.104.0rc1<1.104.0rc2
1.104.0rc2
pip/litellm>=1.103.0<1.103.1
1.103.1
pip/litellm>=1.102.0<1.102.2
1.102.2
pip/litellm>=1.101.0<1.101.3
1.101.3
pip/litellm>=1.91.0<1.100.4
1.100.4

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade pip/litellm to a version that resolves this vulnerability.

    Fixed in 1.104.0rc2
  2. Upgrade

    Upgrade pip/litellm to a version that resolves this vulnerability.

    Fixed in 1.103.1
  3. Upgrade

    Upgrade pip/litellm to a version that resolves this vulnerability.

    Fixed in 1.102.2
  4. Upgrade

    Upgrade pip/litellm to a version that resolves this vulnerability.

    Fixed in 1.101.3
  5. Upgrade

    Upgrade pip/litellm to a version that resolves this vulnerability.

    Fixed in 1.100.4
  6. Upgrade

    Upgrade LiteLLM to a version that resolves this vulnerability.

    Fixed in 1.100.4
  7. Upgrade

    Upgrade LiteLLM to a version that resolves this vulnerability.

    Fixed in 1.101.3
  8. Upgrade

    Upgrade LiteLLM to a version that resolves this vulnerability.

    Fixed in 1.102.2
  9. Upgrade

    Upgrade LiteLLM to a version that resolves this vulnerability.

    Fixed in 1.103.1
  10. Upgrade

    Upgrade LiteLLM to a version that resolves this vulnerability.

    Fixed in 1.104.0-rc.2
  11. Configuration

    Set EXPERIMENTAL_UI_LOGIN=false if you cannot upgrade immediately; this disables the vulnerable authentication path but breaks CLI SSO and Claude Code gateway login.

    LiteLLM EXPERIMENTAL_UI_LOGIN = false

Event History

Oct 22, 2026
CVE Published
via MITRE·06:01 PM
Data Sourced
via MITRE·06:01 PM
DescriptionSeverityWeakness
Data Sourced
via NVD·07:17 PM
DescriptionSeverityWeakness
Oct 27, 2026
Advisory Published
via GitHub·03:04 PM
Data Sourced
via GitHub·03:04 PM
DescriptionSeverityWeaknessAffected Software
Nov 5, 2026
Exploit Published
via GitHub·02:22 PM

Frequently Asked Questions

1

Which deployments are exposed by default?

LiteLLM versions after 1.91.0 in the affected ranges are exploitable in the default configuration. Versions 1.87.0 through 1.90.x require EXPERIMENTAL_UI_LOGIN to be enabled.

2

What level of access does an attacker need?

An attacker must be an authenticated internal user. They need to submit crafted metadata through the API-key flow, obtain the resulting encrypted credential, and replay it as a bearer token.

3

What access can successful exploitation provide?

Successful exploitation causes the proxy to trust a forged proxy administrator identity. This grants administrative access and permits arbitrary commands through the MCP stdio endpoint.

4

Which versions contain fixes?

The issue is fixed in LiteLLM 1.100.4, 1.101.3, 1.102.2, 1.103.1, and 1.104.0-rc.2.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203