Use of Password Hash With Insufficient Computational Effort

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Use of Password Hash With Insufficient Computational Effort via the user/info, user/update, and spend/users API endpoints, which return password hash fields in responses to...

CVE-2026-35030

A flaw was found in LiteLLM, a proxy server for Large Language Model LLM APIs. When JSON Web Token JWT authentication is enabled, the OIDC user information cache uses a truncated portion of the token as a cache key. An unauthenticated attacker can exploit this by crafting a JWT with the same...

CVE-2026-35029

A flaw was found in LiteLLM, an AI Gateway proxy server. An authenticated user can exploit a missing authorization check on the /config/update endpoint. This allows the user to modify proxy configurations and environment variables, leading to remote code execution by registering custom endpoint...

CVE-2026-35030

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.83.0, when JWT authentication is enabled enablejwtauth: true, the OIDC userinfo cache uses token:20 as the cache key. JWT headers produced by the same signing algorithm generate identical first 20...

CVE-2026-35029

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.83.0, the /config/update endpoint does not enforce admin role authorization. A user who is already authenticated into the platform can then use this endpoint to modify proxy configuration and environment...

CVE-2026-35030 LiteLLM has an authentication bypass via OIDC userinfo cache key collision

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.83.0, when JWT authentication is enabled enablejwtauth: true, the OIDC userinfo cache uses token:20 as the cache key. JWT headers produced by the same signing algorithm generate identical first 20...

CVE-2026-35030

LiteLLM (proxy for LLM APIs) contains an authentication bypass flaw when JWT/OIDC authentication is enabled. The OIDC userinfo cache key is derived from the first 20 characters of the token, allowing an unauthenticated attacker to craft a token whose prefix matches a legitimate user’s cached toke...

CVE-2026-35030 LiteLLM has an authentication bypass via OIDC userinfo cache key collision

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.83.0, when JWT authentication is enabled enablejwtauth: true, the OIDC userinfo cache uses token:20 as the cache key. JWT headers produced by the same signing algorithm generate identical first 20...

CVE-2026-35029 LiteLLM affected by privilege escalation via unrestricted proxy configuration endpoint

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.83.0, the /config/update endpoint does not enforce admin role authorization. A user who is already authenticated into the platform can then use this endpoint to modify proxy configuration and environment...

CVE-2026-35029

CVE-2026-35029 affects LiteLLM, a proxy AI Gateway. The /config/update endpoint lacks admin authorization, allowing an authenticated user to modify proxy config and environment variables, register attacker-controlled Python code handlers, achieve remote code execution, read arbitrary server files...

CVE-2026-35029 LiteLLM affected by privilege escalation via unrestricted proxy configuration endpoint

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.83.0, the /config/update endpoint does not enforce admin role authorization. A user who is already authenticated into the platform can then use this endpoint to modify proxy configuration and environment...

CVE-2026-35029

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.83.0, the /config/update endpoint does not enforce admin role authorization. A user who is already authenticated into the platform can then use this endpoint to modify proxy configuration and environment...

How LiteLLM Turned Developer Machines Into Credential Vaults for Attackers

The most active piece of enterprise infrastructure in the company is the developer workstation. That laptop is where credentials are created, tested, cached, copied, and reused across services, bots, build tools, and now local AI agents. In March 2026, the TeamPCP threat actor proved just how...

LiteLLM 授权问题漏洞

LiteLLM is an open-source application developed by Berri AI. It allows for the invocation of all LLM APIs in the OpenAI format. Prior to version 1.83.0, LiteLLM had an authorization vulnerability. This vulnerability stemmed from the use of token:20 as a cache key when JWT authentication was...

Privilege Escalation

LiteLLM is vulnerable to Privilege Escalation. The vulnerability is due to missing admin authorization checks on the /config/update endpoint, which allows an authenticated attacker to modify configurations, execute arbitrary code, and access sensitive data...

CVE-2026-34936

PraisonAI is a multi-agent teams system. Prior to version 4.5.90, passthrough and apassthrough in praisonai accept a caller-controlled apibase parameter that is concatenated with endpoint and passed directly to httpx.Client.request when the litellm primary path raises AttributeError. No URL schem...

User Impersonation

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to User Impersonation in the getoidcuserinfo function. An attacker can gain unauthorized access to another user's identity and permissions by crafting a token with the same...

AI Firm Mercor Confirms Breach as Hackers Claim 4TB of Stolen Data

AI firm Mercor confirms a breach linked to a LiteLLM supply chain attack, as hackers claim to have stolen 4TB of sensitive data and internal systems...

LiteLLM 1.82.7 / 1.82.8 Supply Chain Compromise (GHSA-5mg7-485q-xm76)

The version of the LiteLLM Python package installed on the remote host is 1.82.7 or 1.82.8. These versions were published to PyPI by a threat actor known as TeamPCP using compromised maintainer credentials obtained through the Aqua Security Trivy supply chain attack. The malicious releases contai...

Missing Authentication for Critical Function

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Missing Authentication for Critical Function in the key-management endpoints due to improper enforcements of proxy-admin, team-admin, org-admin, or ownership checks. An...