vLLM Deserialization of Untrusted Data vulnerability
CVE-2024-11041 · GHSA-5vqr-wprc-cpp7 · published 2025-03-20 · updated 2025-03-21
- Severity
- Critical
- CVSS score
- 9.8
- Chance of exploitation (EPSS)
- 1.7%
- Fixed in
- No fix yet
- Exploitation Public proof of concept
- Automatable Yes
- Technical impact Total
- CISA SSVC
vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses pickle.loads to parse received sockets directly, leading to a remote code execution vulnerability. An attacker can exploit this by sending a malicious payload to the MessageQueue, causing the victim's machine to execute arbitrary code.
No fixed release is listed yet for vllm. Follow the source advisory for updates, and until one ships:
General guidance from ShieldPi, not a vendor fix
- Unsafe deserialization. Do not let it load files, models or data from sources you do not trust, and keep its RPC and socket ports reachable only from localhost or hosts you trust.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | <= 0.6.2 | No fix yet |
- CriticalLMDeploy has Remote Code Execution by Pickle Deserialization via handle_zmq_recv in lmdeploy/lmdeploy/pytorch/disagg/conn/engine_conn.pylmdeploy
- CriticalLMdeploy has Remote Code Execution by Pickle Deserialization via zmq_rpc.call_and_response() in InterLM/lmdeploylmdeploy
- CriticalSGLang: Unauthenticated RCE via --enable-custom-logit-processorsglang
- CriticalSGLanG: Multimodal scheduler deserializes untrusted pickle data on 0.0.0.0 ROUTER socketsglang
- Criticaln8n: HTTP Request Node Pagination Prototype Pollution to RCEn8n, n8n, n8n
- Criticaln8n Has an XML Node Prototype Pollution Patch Bypassn8n, n8n, n8n
- CriticalvLLM: OpenAI auth bypassvllm
- CriticalvLLM has RCE In Video Processingvllm
- CriticalvLLM Allows Remote Code Execution via PyNcclPipe Communication Servicevllm
- CriticalvLLM Vulnerable to Remote Code Execution via Mooncake Integrationvllm
- CriticalCVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0vllm
- CriticalvLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypointsvllm
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.