Bug 2541509 (CVE-2026-89032)

Summary: CVE-2026-89032 litellm: LiteLLM: Information disclosure via semantic cache metadata mismatch
Product: [Other] Security Response Reporter: OSIDB Bzimport <bzimport>
Component: vulnerabilityAssignee: Product Security <prodsec-ir-bot>
Status: NEW --- QA Contact:
Severity: high Docs Contact:
Priority: high    
Version: unspecifiedCC: dschmidt, ebourniv, hasun, ikhan, ilpinto, jlanda, jwong, kshier, ltomasbo, nyancey, omaciel, ptisnovs, rbobbitt, sbunciak, simaishi, stcannon, ttakamiy, yguenane, ykashtan
Target Milestone: ---Keywords: Security
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: ---
Doc Text:
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.
 Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:

Description OSIDB Bzimport 2026-09-25 16:44:20 UTC 
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.