436 matches found
CVE-2026-31958 vulnerabilities
Vulnerabilities for packages: tensorflow-cpu-jupyter, mitmproxy, tensorflow-gpu-jupyter, litellm, kubeflow-pipelines-visualization-server, airflow, dask-kubernetes...
GHSA-QJXF-F2MG-C6MC vulnerabilities
Vulnerabilities for packages: tensorflow-cpu-jupyter, mitmproxy, tensorflow-gpu-jupyter, litellm, kubeflow-pipelines-visualization-server, airflow, dask-kubernetes...
CVE-2026-31826 vulnerabilities
Vulnerabilities for packages: nemo, open-webui, litellm...
GHSA-HQMH-PPP3-XVM7 vulnerabilities
Vulnerabilities for packages: nemo, open-webui, litellm...
CVE-2026-28804 vulnerabilities
Vulnerabilities for packages: litellm...
GHSA-9M86-7PMV-2852 vulnerabilities
Vulnerabilities for packages: litellm...
PT-2026-42539
Name of the Vulnerable Software and Affected Versions LiteLLM versions prior to 1.83.10 Description An issue exists where the '/user/update' endpoint does not restrict which fields a user can modify when updating their own account. This allows a user to change their user role to proxy admin,...
PT-2026-31920
Name of the Vulnerable Software and Affected Versions LiteLLM versions through 2026-04-08 Description LiteLLM through 2026-04-08 allows remote attackers to execute arbitrary code via bytecode rewriting at the /guardrails/test custom code URI. Recommendations Update LiteLLM to a version later than...
Insertion of Sensitive Information into Log File
Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Insertion of Sensitive Information into Log File via the userapikeyauthbuilder function, which leaks expired session keys into the authentication error output of other...
GHSA-HX9Q-6W63-J58V vulnerabilities
Vulnerabilities for packages: authentik, emissary, datadog-agent-fips, datadog-agent, litellm, kserve, authentik-fips...
CVE-2025-67221 vulnerabilities
Vulnerabilities for packages: authentik, emissary, datadog-agent-fips, datadog-agent, litellm, kserve, authentik-fips...
CVE-2024-2952
BerriAI/litellm is vulnerable to Server-Side Template Injection SSTI via the /completions endpoint. The vulnerability arises from the hfchattemplate method processing the chattemplate parameter from the tokenizerconfig.json file through the Jinja template engine without proper sanitization...
Information Exposure
Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Information Exposure due to improper masking of raw request headers in the precall method of litellm/litellmcoreutils/litellmlogging.py. An attacker can obtain exposed API...
Insertion of Sensitive Information into Externally-Accessible File or Directory
Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Insertion of Sensitive Information into Externally-Accessible File or Directory due to incomplete masking of OCI secret fields in responses from the /models and /v1/models...
Insertion of Sensitive Information into Log File
Overview litellm is a Library to easily interface with LLM API providers Affected versions of this package are vulnerable to Insertion of Sensitive Information into Log File via the getredirectresponsefromopenid and forwardupstreamtoclient functions. An attacker can obtain sensitive authenticatio...
EUVD-2025-36712
LiteLLM Information health APIKEY Information Disclosure Vulnerability. This vulnerability allows remote attackers to disclose sensitive information on affected installations of LiteLLM. Authentication is required to exploit this vulnerability. The specific flaw exists within the handling of the...
CVE-2025-11203
LiteLLM Information health APIKEY Information Disclosure Vulnerability. This vulnerability allows remote attackers to disclose sensitive information on affected installations of LiteLLM. Authentication is required to exploit this vulnerability. The specific flaw exists within the handling of the...
CVE-2025-11203 LiteLLM Information health API_KEY Information Disclosure Vulnerability
LiteLLM Information health APIKEY Information Disclosure Vulnerability. This vulnerability allows remote attackers to disclose sensitive information on affected installations of LiteLLM. Authentication is required to exploit this vulnerability. The specific flaw exists within the handling of the...
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...