BerriAI LiteLLM < 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer
Key facts
- Attack vector
- Network
- Privileges required
- Low
- User interaction
- Passive
- Attack complexity
- High
- Attack requirements
- None
- Impact type
- Security bypass
- Confidentiality · integrity · availability
- High · High · None
- Fix status
- Partial Red Hat: 1 fixed, 4 without a fix
Attack profile from CVSS 4.0 · CNA. Fix status from CNA and Red Hat. Impact type from CWE-863.
Summary
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
Remediation
- Fix · CNA litellm (BerriAI) Fixed in 1.101.0-rc.1
Red Hat 1 advisory
- RHSA-2026:84734 Released 2026-10-19 · Red Hat rating CriticalRHOAI 3.4.5 - Red Hat OpenShift AI
- Red Hat OpenShift AI 3.4 registry.redhat.io/rhoai/odh-ai-gateway-payload-processing-rhel9, registry.redhat.io/rhoai/odh-automl-rhel9, registry.redhat.io/rhoai/odh-autorag-rhel9 +47
Vendor assessments
Red Hat
Red Hat rating: Important. Red Hat's page for this CVE →
| Product | Status | Plan or fix |
|---|---|---|
| Exploit Intelligence | Affected | No fix yet |
| Lightspeed Core | Affected | No fix yet |
| Red Hat Ansible Automation Platform 2 | Affected | No fix yet |
| Red Hat OpenShift AI (RHOAI) | Affected | No fix yet |
| Red Hat OpenShift AI 3.4 | Fixed | RHSA-2026:84734 |
Not affected: 1 product
- Red Hat OpenShift AI 3.4
Timeline
- 2026-10-02 Threatist record created from CVE-2026-89032
- 2026-10-03 Alias added: GHSA-237m-2qxv-ww7c
- 2026-10-10 Affected versions changed · Red Hat
- 2026-10-15 Affected versions changed · Red Hat
- 2026-10-20 Fix available: RHSA-2026:84734 · Red Hat
- 2026-10-20 Fix available: Red Hat OpenShift AI 3.4 · Red Hat
References
More BerriAI vulnerabilities
- TI-2026-26015 Trivy ecosystem supply chain briefly compromised KEVCVSS 4.0CRITICAL 9.4
- TI-2026-30529 LiteLLM: SQL injection in Proxy API key verification KEVCVSS 4.0CRITICAL 9.3
- TI-2026-30582 LiteLLM: Authenticated command execution via MCP stdio test endpoints KEVCVSS 4.0HIGH 8.7
- TI-2026-42639 LiteLLM: MCP Authentication Bypass via OAuth2 Passthrough Fallback KEVCVSS 4.0HIGH 8.8
- TI-2024-05340 Remote Code Execution in BerriAI/litellm CVSS 3.1CRITICAL 9.8
- TI-2024-03969 Remote Code Execution in berriai/litellm CVSS 3.0CRITICAL 9.8
Sources
- CVE-2026-89032 · CVE Program
- CVE-2026-89032 · NVD
- FIRST EPSS
- GHSA-237m-2qxv-ww7c · GitHub Advisory Database · CC BY 4.0
- CVE-2026-89032 · Red Hat security data · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences