{"id":"CVE-2026-89032","title":"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_s…","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_s…","severity":"high","cvss":7.7,"cvssVector":"CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:N","cwe":["CWE-863"],"vendor":"BerriAI","product":"litellm","affected":["litellm < 1.101.0-rc.1"],"published":"2026-09-25","updated":"2026-09-25","sourceUpdated":"2026-09-25T17:17:18.793","source":"NVD","sourceUrl":"https://nvd.nist.gov/vuln/detail/CVE-2026-89032","references":[{"url":"https://github.com/BerriAI/litellm/commit/16db51e2cfc28e02bd460481e634a8403ea9265e","label":"disclosure@vulncheck.com"},{"url":"https://github.com/BerriAI/litellm/pull/39590","label":"disclosure@vulncheck.com"},{"url":"https://github.com/BerriAI/litellm/releases/tag/v1.101.0-rc.1","label":"disclosure@vulncheck.com"},{"url":"https://www.vulncheck.com/advisories/berriai-litellm-rc-1-tenant-isolation-bypass-via-semantic-cache-layer","label":"disclosure@vulncheck.com"}],"tags":["nvd","cve.org"],"ingestedAt":"2026-09-25T17:13:14.030Z","slug":"CVE-2026-89032","body":"## Overview\n\nBerriAI 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.\n\n## Remediation\n\nRefer to the linked advisories for vendor-supplied fixes and affected version ranges.","depth":"twilight","depthScore":42,"depthScoreParts":{"impact":42.4,"likelihood":0,"exploitation":0,"ransomware":0},"changes":[]}