CVE-2026-89032
BerriAI LiteLLM < 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer
No known exploitation. No EPSS score yet. No fix published yet.
What to do
No fixed build or workaround is published yet. Limit exposure and watch for a patch.
What it is
From the CVE record
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.
In plain language
No plain-language summary for this CVE yet.
Exploitation
Where each signal puts this CVE on the scale from published to confirmed exploited.
- CISA KEV
Not in the catalog. CISA has not confirmed exploitation.
- Public exploits
No public exploit or proof of concept found in the sources we track.
- EPSS
No EPSS score yet. New CVEs are usually scored within a few days.
Lifecycle
4 events over 0 days, from the signal feeds we watch.
- Publishedweakness classified, att&ck mapped, record updated
Affected products
Technical detail
CVSS 3.1 vector
Open in the CVSS calculatorCVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:N
Scored 7.7 by NVD.
How it is reached
- Attack Vector NetworkExploitable remotely over the network without any special conditions
- Attack Complexity HighRequires specific conditions like a race condition or non-default configuration
- Privileges Required LowRequires basic user-level privileges
- User Interaction RequiredA user must click a link, open a file, or perform some action
Scope
- Scope ChangedThe exploit can affect other components (e.g. sandbox escape, host compromise from VM)
Impact if exploited
- Confidentiality HighTotal information disclosure — all data in the component is compromised
- Integrity HighTotal loss of integrity — attacker can modify any data in the component
- Availability NoneNo availability impact
Weaknesses
ATT&CK techniques
Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.
Sources
References in the record
- github.com/BerriAI/litellm/commit/16db51e2cfc28e02bd460481e634a8403ea9265e
- github.com/BerriAI/litellm/pull/39590
- github.com/BerriAI/litellm/releases/tag/v1.101.0-rc.1
And 1 more reference. See all after sign-in
Watch the software you run.
My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.
We'll flag the next CVE, public exploit or patch for Litellm, not every advisory.
A free account adds
- The full version matrix and every affected product
- Exploit links, proofs of concept and Metasploit modules
- Email alerts for the products you watch
- The same data over REST API, MCP and CLI