PT-2026-53473

Impact A Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from request.url.path in litellm/proxy/auth/auth utils.py::get request route, which Starlette reconstruc...

semantic-router exposed to compromised litellm wheel (CVE-2026-42208) via unbounded transitive pin

Impact semantic-router versions 0.1.8 through 0.1.14 declare litellm=1.61.3 with no upper bound. During the window in which litellm==1.82.8 was the latest release on PyPI, a fresh install of any affected semantic-router version could resolve to that compromised wheel. The malicious litellm==1.82....

GHSA-98X5-VQ43-VC5P semantic-router exposed to compromised litellm wheel (CVE-2026-42208) via unbounded transitive pin

Impact semantic-router versions 0.1.8 through 0.1.14 declare litellm=1.61.3 with no upper bound. During the window in which litellm==1.82.8 was the latest release on PyPI, a fresh install of any affected semantic-router version could resolve to that compromised wheel. The malicious litellm==1.82....

Weekly Metasploit Update: Modules for Audiobookshelf, LiteLLM, Next.js, Dalfox and more

Help shape the future of Metasploit Framework We are planning future work in relation to the evasion capabilities present in Metasploit Framework, and how they function/are presented to users. We are currently accepting responses to our feedback form, which means that you can shape the future of...

CVE-2026-12773

A flaw was found in BerriAI litellm, within its MCP Proxy component. A remote attacker could exploit an improper authentication vulnerability in the UserAPIKeyAuth function. This could allow unauthorized access, potentially compromising the confidentiality, integrity, and availability of data...

CVE-2026-47101

A flaw was found in LiteLLM. An authenticated internal user can exploit this vulnerability by creating API keys that grant access to routes beyond their assigned role. This occurs because the system fails to verify if the specified allowedroutes for the API key align with the user's actual...

CVE-2026-12770

A flaw was found in BerriAI litellm. A remote attacker could exploit an improper authorization vulnerability within the Admin Key Handler component. This could allow the attacker to perform unauthorized actions, leading to limited impacts on data integrity and service availability...

CVE-2026-49468

A flaw was found in LiteLLM, a proxy server AI Gateway used to call Large Language Model LLM APIs. A remote attacker could exploit a Host-header parsing vulnerability in the proxy authentication layer. By sending a crafted Host header, an attacker could gain unauthenticated access to protected...

The vulnerability of the `internal_user` function in the LiteLLM proxy server allows a hacker to increase their privileges and gain full control over the proxy server.

The vulnerability of the internaluser function in the LiteLLM proxy server is related to deficiencies in the authentication process. Exploiting this vulnerability allows a malicious actor to enhance their privileges and gain full control over the proxy server...

GHSA-4XGF-CPJX-PC3J vulnerabilities

Vulnerabilities for packages: litellm, open-webui, mcp-atlassian, prefect-fips, airflow, vllm-cuda-13.2, vllm-openai-cuda-13.0, airflow-core, airflow-postgres-fips, tritonserver-backend-vllm-cuda-12.9, azureml-inference-server-http-fips, tritonserver-backend-vllm-cuda-13.0, lmcache-cuda-12.8,...

CVE-2026-12799

A flaw was found in BerriAI litellm. A remote attacker could exploit an improper authorization vulnerability in the uiviewusers function to gain access to sensitive information. This issue is related to an incomplete fix for a previous vulnerability. Mitigation To reduce exposure, restrict networ...

CVE-2026-12774

A flaw was found in BerriAI litellm. A remote attacker could exploit a Server-Side Request Forgery SSRF vulnerability in the MCP Server Connection Testing component. This flaw, specifically within the executewithmcpclient function, allows an attacker to trick the server into making unauthorized...

CVE-2026-12796

A flaw was found in BerriAI litellm. A remote attacker could exploit a vulnerability in the getredirectresponsefromopenid function within the SSO Authentication Flow component. This manipulation leads to session expiration, potentially causing a denial of service for authenticated users. Mitigati...

CVE-2026-49468 LiteLLM: Authentication Bypass via Host Header Injection

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from...

CVE-2026-49468 LiteLLM: Authentication Bypass via Host Header Injection

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from...

EUVD-2026-38361

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.84.0, This vulnerability is fixed in 1.84.0...

CVE-2026-12799

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...

CVE-2026-12798

A weakness has been identified in BerriAI litellm up to 1.82.2. Affected by this vulnerability is the function loadopenapispecasync of the file litellm/proxy/experimental/mcpserver/openapitomcpgenerator.py of the component MCP OpenAPI Spec Loader. This manipulation of the argument specpath causes...

CVE-2026-12797

A security flaw has been discovered in BerriAI litellm up to 1.82.5. Affected is the function asyncprecallhook of the file enterprise/enterprisehooks/bannedkeywords.py of the component Completions Interface. The manipulation of the argument prompt results in incorrect authorization. The attack ma...

CVE-2026-12796

A vulnerability was identified in BerriAI litellm up to 1.82.2. This impacts the function getredirectresponsefromopenid of the file litellm/proxy/managementendpoints/uisso.py of the component SSO Authentication Flow. The manipulation leads to session expiration. The attack is possible to be carri...