BerriAI LiteLLM up to 1.100.3/1.101.2/1.102.1/1.103.0 MCP stdio endpoint authentication replay

Summaryinfo

A vulnerability classified as critical was found in BerriAI LiteLLM up to 1.100.3/1.101.2/1.102.1/1.103.0. This vulnerability affects unknown code of the component MCP stdio endpoint. Executing a manipulation can lead to authentication replay. This vulnerability is tracked as CVE-2026-114612. The attack can be launched remotely. No exploit exists. Upgrading the affected component is advised.

Detailsinfo

A vulnerability has been found in BerriAI LiteLLM up to 1.100.3/1.101.2/1.102.1/1.103.0 and classified as critical. This vulnerability affects an unknown function of the component MCP stdio endpoint. The manipulation with an unknown input leads to a authentication replay vulnerability. The CWE definition for the vulnerability is CWE-294. A capture-replay flaw exists when the design of the product makes it possible for a malicious user to sniff network traffic and bypass authentication by replaying it to the server in question to the same effect as the original message (or with minor changes). As an impact it is known to affect confidentiality, integrity, and availability. CVE summarizes:

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.

The advisory is available at github.com. This vulnerability was named CVE-2026-114612 since 10/21/2026. The exploitation appears to be easy. The attack can be initiated remotely. No form of authentication is required for a successful exploitation. The technical details are unknown and an exploit is not available. This vulnerability is assigned to T1040 by the MITRE ATT&CK project.

Upgrading to version 1.100.4, 1.101.3, 1.102.2, 1.103.1 or 1.104.0-rc.2 eliminates this vulnerability.

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Productinfo

Vendor

• BerriAI

Name

• LiteLLM

Version

• 1.100.0
• 1.100.1
• 1.100.2
• 1.100.3
• 1.101.0
• 1.101.1
• 1.101.2
• 1.102.0
• 1.102.1
• 1.103

Website

• Product: https://github.com/BerriAI/litellm/

CPE 2.3info

• 🔒
• 🔒
• 🔒

CPE 2.2info

• 🔒
• 🔒
• 🔒

CVSSv4info

CVSSv3info

CVSSv2info

Exploitinginfo

Threat Intelligenceinfo

Countermeasuresinfo

Timelineinfo

Sourcesinfo

Entryinfo

If you want to get best quality of vulnerability data, you may have to visit VulDB.

Discussion