vLLMGHSA-cj47-qj6g-x7r4
vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints
Critical9.8CVE-2024-9053 · Published Mar 20, 2025 · updated Aug 7, 2026
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints. The core functionality run_server_loop() calls the function _make_handler_coro(), which directly uses cloudpickle.loads() on received messages without any sanitization. This can result in remote code execution by deserializing malicious pickle data.
Affected versions
| Package | Affected | Fixed in |
|---|---|---|
| vllm PyPI | <= 0.6.0 | No fix yet |
Details and references
More vLLM advisories
All vLLM| Date | Advisory | Severity | Fixed in |
|---|---|---|---|
| Apr 232025 | vLLM: code execution | Critical9.8 | 0.8.0 |
| Apr 152025 | vLLM vulnerable to Denial of Service by abusing xgrammar cache | Medium6.5 | 0.8.4 |
| Mar 202025 | vLLM deserialization vulnerability in vllm.distributed.GroupCoordinator.recv_object | Critical9.8 | No fix yet |
| Mar 202025 | vLLM Deserialization of Untrusted Data vulnerability | Critical9.8 | No fix yet |
| Mar 192025 | vLLM Allows Remote Code Execution via Mooncake Integration | Critical9.0 | 0.8.0 |
| Mar 192025 | vLLM denial of service via outlines unbounded cache on disk | Medium6.5 | 0.8.0 |