Authenticated cross-tenant disclosure via cache scope mismatch
Published Sep 25, 2026 · Updated Sep 25, 2026
Tenant isolation bypass in Berri AI LiteLLM before 1.101.0-rc.1 allows remote authenticated users to read other tenants' cached responses. The semantic cache derives tenant scope with _get_semantic_cache_tenant_scope() but looks up a different metadata key through _get_metadata_variable_name(), allowing similar prompts to cross principal boundaries. A valid virtual key and an enabled semantic cache are required; exposed responses can contain sensitive data or tool-call payloads executed by agentic clients.
Summary
What happened
Tenant isolation bypass in Berri AI LiteLLM before 1.101.0-rc.1 allows remote authenticated users to read other tenants' cached responses. The semantic cache derives tenant scope with _get_semantic_cache_tenant_scope() but looks up a different metadata key through _get_metadata_variable_name(), allowing similar prompts to cross principal boundaries. A valid virtual key and an enabled semantic cache are required; exposed responses can contain sensitive data or tool-call payloads executed by agentic clients.
The record
- CVE
- CVE-2026-89032
- Published
- Sep 25, 2026
- Updated
- Sep 25, 2026
- Vendor
- Berri AI
- Product
- LiteLLM
- Classifications
- T1213
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Sep 25, 2026CVE publishedPublication date reported by the CVE source.
- Sep 25, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0 <1.101.0-rc.1
What conditions does exploitation require?
What is affected?
Published CVSS scores
No CVSS assessment is available in this record.
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Activity data is delayed. The latest report is Sep 28, 2026.
Weakness, pattern, technique
Public exploit references
- Cross-tenant response-cache reuse reproductionproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Get started to see how Hinoki identifies affected software and validates exploitability in your environment.
Get started