Логотип exploitDog
Консоль
Логотип exploitDog

exploitDog

redhat логотип

CVE-2026-89032

Опубликовано: 25 сент. 2026
Источник: redhat
CVSS3: 7.7
EPSS Низкий

Описание

BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants' cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants' personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal.

A flaw was found in LiteLLM. Due to a metadata key mismatch in the semantic cache component, an authenticated remote attacker can bypass tenant isolation by submitting semantically similar queries. This issue leads to information disclosure, allowing unauthorized access to cached responses containing other tenants' sensitive data, and may cause connected automated agents to execute unauthorized actions under victim credentials.

Отчет

This vulnerability is rated as Important severity because authenticated multi-tenant users can bypass isolation boundaries to access confidential response data and trigger unauthorized tool execution across distinct accounts. While exploitation requires valid API access to affected proxy routes, the shared caching mechanism compromises confidentiality and integrity across AI workloads. Deployments serving single-tenant workloads or environments where semantic caching is not shared between untrusted tenants face substantially reduced exposure.

Меры по смягчению последствий

Mitigation for this issue is either not available or the currently available options do not meet the Red Hat Product Security criteria comprising ease of use and deployment, applicability to widespread installation base, or stability.

Затронутые пакеты

ПлатформаПакетСостояниеРекомендацияРелиз
Exploit Intelligenceexploit-intelligence/vulnerability-analysis-rhel9Affected
Lightspeed Corelightspeed-core/lightspeed-stack-rhel9Affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-26/lightspeed-chatbot-rhel9Affected
Red Hat Ansible Automation Platform 2ansible-automation-platform-27/lightspeed-chatbot-rhel9Affected
Red Hat OpenShift AI (RHOAI)rhoai/odh-llama-stack-core-rhel9Affected
Red Hat OpenShift AI 3.4rhoai/odh-trustyai-garak-lls-provider-dsp-rhel9FixedRHSA-2026:8473419.10.2026
Red Hat OpenShift AI 3.5rhoai/odh-mlflow-rhel9FixedRHSA-2026:9587206.11.2026
Red Hat OpenShift AI 3.5rhoai/odh-th-torch-cpu-py312-rhel9FixedRHSA-2026:9587206.11.2026
Red Hat OpenShift AI 3.5rhoai/odh-th-torch-cuda-py312-rhel9FixedRHSA-2026:9587206.11.2026

Показывать по

Дополнительная информация

Статус:

Important
Дефект:
CWE-524
https://bugzilla.redhat.com/show_bug.cgi?id=2541509litellm: LiteLLM: Information disclosure via semantic cache metadata mismatch

EPSS

Процентиль: 20%
0.00272
Низкий

7.7 High

CVSS3

Связанные уязвимости

CVSS3: 7.7
nvd
около 2 месяцев назад

BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants' cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants' personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal.

CVSS3: 7.7
github
около 2 месяцев назад

BerriAI LiteLLM before 1.101.0-rc.1 contains a tenant isolation bypass vulnerability in the semantic cache layer that allows authenticated users to read other tenants' cached responses by exploiting a metadata key mismatch between _get_semantic_cache_tenant_scope() and _get_metadata_variable_name(). Attackers holding a valid virtual key can submit semantically similar prompts on affected routes such as /v1/responses and /bedrock/* to retrieve cached responses containing other tenants' personally identifiable information, financial data, or source code, and can cause agentic front-ends to auto-execute attacker-supplied tool calls under victim credentials by returning cached function_call or tool_calls payloads to a different principal.

EPSS

Процентиль: 20%
0.00272
Низкий

7.7 High

CVSS3