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.
https://github.com/BerriAI/litellm/releases/tag/v1.101.0-rc.1
https://github.com/BerriAI/litellm/pull/39590
https://github.com/BerriAI/litellm/commit/16db51e2cfc28e02bd460481e634a8403ea9265e
Published: 2026-09-25
Updated: 2026-10-01
Base Score: 6.6
Vector: CVSS2#AV:N/AC:H/Au:S/C:C/I:C/A:N
Severity: Medium
Base Score: 7.7
Vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:N
Severity: High
Base Score: 8.7
Vector: CVSS:4.0/AV:N/AC:H/AT:N/PR:L/UI:P/VC:H/VI:H/VA:N/SC:H/SI:H/SA:N
Severity: High
EPSS: 0.00272