Opening SecureFlowLiteLLM CVE-2026-89032: Broken Semantic-Cache Isolation Enables Cross-User Leaks and Tool-Call Poisoning
Case summary & sources

AIDEFEND SecureFlow / SecureFlow Case Index

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.T0040 AI Model Inference API Access
  • AML.T0085.002 Conversation Context and Memory
  • AML.T0130 AI Agent Response Biasing
  • AML.T0053 AI Agent Tool Invocation
  • AML.T0050 Command and Scripting Interpreter

Source