LiteLLM: Local file read via request-supplied OIDC file references

ImpactLiteLLM's /health/testconnection endpoint resolved request-supplied environment and OIDC file references in litellmparams. A proxy administrator, or another privileged caller with permission to test model connections, could cause LiteLLM to read files from the local filesystem via an...

CVE-2026-52870 vulnerabilities

Vulnerabilities for packages: semgrep, litellm...

External Control of File Name or Path

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to External Control of File Name or Path via request-supplied OIDC file references through the /health/testconnection handler in litellm/proxy/healthendpoints/healthendpoints....

PYSEC-2026-1545 LiteLLM Vulnerable to Denial of Service (DoS) via Crafted HTTP Request

A Denial of Service DoS vulnerability exists in berriai/litellm version v1.44.5. This vulnerability can be exploited by appending characters, such as dashes -, to the end of a multipart boundary in an HTTP request. The server continuously processes each character, leading to excessive resource...

PYSEC-2026-1540 Arbitrary file deletion in litellm

BerriAI's litellm, in its latest version, is vulnerable to arbitrary file deletion due to improper input validation on the /audio/transcriptions endpoint. An attacker can exploit this vulnerability by sending a specially crafted request that includes a file path to the server, which then deletes...

litellm passes untrusted data to `eval` function without sanitization

A remote code execution RCE vulnerability exists in the berriai/litellm project due to improper control of the generation of code when using the eval function unsafely in the litellm.getsecret method. Specifically, when the server utilizes Google KMS, untrusted data is passed to the eval function...

GHSA-4XGF-CPJX-PC3J vulnerabilities

Vulnerabilities for packages: vllm-openai-cuda-13.0, litellm, prefect, semgrep, airflow, azureml-inference-server-http, azureml-inference-server-http-fips, airflow-core, lmcache-cuda-12.8, mcp-atlassian, open-webui, tritonserver-backend-vllm-cuda-12.9, prefect-fips,...

Incorrect Authorization

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Incorrect Authorization in the BannedKeywords enterprise and AzureContentSafety hooks of the Completions Interface. An attacker can gain unauthorized access to restricted...

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 /sso/debug/login and /sso/debug/callback endpoints in the SSO Debug Flow. An attacker can gain unauthorized access and...

CVE-2026-12799 BerriAI litellm Incomplete Fix CVE-2025-0628 internal_user_endpoints.py ui_view_users improper authorization

A security vulnerability has been detected in BerriAI litellm up to 1.82.2. Affected by this issue is the function uiviewusers of the file litellm/proxy/managementendpoints/internaluserendpoints.py of the component Incomplete Fix CVE-2025-0628. Such manipulation leads to improper authorization. I...

Server-side Request Forgery (SSRF)

Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Server-side Request Forgery SSRF via the /v1/mcp/test/connection endpoint. An attacker can perform server-side request forgery SSRF by supplying a crafted tokenurl and...

CVE-2026-12774

CVE-2026-12774 affects BerriAI litellm up to 1.82.2. The vulnerability targets the function _execute_with_mcp_client in litellm/proxy/_experimental/mcp_server/rest_endpoints.py (MCP Server Connection Testing). It enables server‑side request forgery through manipulation of this component, with rem...

VulnCheck KEV: CVE-2026-42271

BerriAI LiteLLM contains a command injection vulnerability that could allow any authenticated user, including holders of low-privilege internal-user keys, to run arbitrary commands on the host...

CVE-2026-47102

LiteLLM prior to 1.83.10 allows a user to modify their own userrole via the /user/update endpoint. While the endpoint correctly restricts users to updating only their own account, it does not restrict which fields may be changed. A user who can reach this endpoint can set their role to proxyadmin...

Exploit for SQL Injection in Litellm

Threat Intelligence Brief - CVE-2026-42208: BerriAI LiteLLM SQ...

CVE-2026-41168 vulnerabilities

Vulnerabilities for packages: nemo, open-webui, litellm...

LiteLLM 信息泄露漏洞

LiteLLM is an open source application from Berri AI. All LLM APIs can be called using the OpenAI format. LiteLLM suffers from an information disclosure vulnerability that stems from exposing sensitive information when handling the health endpoint APIKEY parameter, which could lead to credential...

EUVD-2025-6882

Malicious code in bioql PyPI...

CVE-2024-4888

BerriAI's litellm, in its latest version, is vulnerable to arbitrary file deletion due to improper input validation on the /audio/transcriptions endpoint. An attacker can exploit this vulnerability by sending a specially crafted request that includes a file path to the server, which then deletes...

Remote Code Execution (RCE)

litellm is vulnerable to Remote Code Execution RCE. The vulnerability is due to improper handling of the 'postcallrules' configuration, allowing an attacker to specify a system method as a callback, leading to arbitrary command execution...