NVISO Labs
aidefend-sf0098
LiteLLM CVE-2026-89032: Broken Semantic-Cache Isolation Enables Cross-User Leaks and Tool-Call Poisoning
- AI Infrastructure
- Tool Integrations & MCP
- Autonomous Agents
- Data Exfiltration
- Model Poisoning & Integrity
- Financial Fraud & Abuse
- System Compromise & RCE
LiteLLM is a gateway that routes applications' requests to language models. Its semantic cache can reuse an earlier answer when two questions have similar meanings. NVISO showed that in the tested configuration, /v1/responses reused cached entries across different API keys. This exposed simulated support data and allowed a fabricated answer or tool-call response to reach a different user. The researchers also demonstrated downstream execution in a mock banking tool and the pi coding agent. CVE-2026-89032 was fixed in v1.101.0-rc.1.
Mapped threat techniques
AML.T0040AI Model Inference API AccessAML.T0085.002Conversation Context and MemoryAML.T0130AI Agent Response BiasingAML.T0053AI Agent Tool InvocationAML.T0050Command and Scripting Interpreter