Vulnerability · Published Sep 25, 2026 · Assigned by VulnCheck

CVE-2026-89032BerriAI LiteLLM < 1.101.0-rc.1 Tenant Isolation Bypass via Semantic Cache Layer

High 7.7

In plain English

A high-severity incorrect authorization in litellm from BerriAI. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.3% (higher than 20% of all known vulnerabilities).

Severity (CVSS 3.1)7.7High

Exploit odds (30 days)0.3%top 80.3% of all CVEs

Exploited in the wildNo reportsCISA SSVC: none

Attack toolingNoneno public tooling known

Official description

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.

Affected products (as reported)

Vendor	Product	Versions
BerriAI	litellm	0 – before 1.101.0-rc.1

Weakness: CWE-863 · Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:N

References

LiteLLM v1.101.0-rc.1 Release Notes release-notes
Pull Request issue-tracking, patch
Patch Commit patch
https://www.vulncheck.com/advisories/berriai-litellm-rc-1-tenant-isolation-bypass-via-semantic-cache-layer third-party-advisory