Browse / AI Framework and Platform Flaws / CVE-2024-9053
vLLM allows Remote Code Execution by Pickle Deserialization via AsyncEngineRPCServer() RPC server entrypoints
- Class
- AI Framework and Platform Flaws (filed by a model that read the source)
- Technique
- Unsafe deserialisation
- Affected
- vllm (PyPI)
- CVSS
- CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 1.4% chance of exploitation in 30 days
How it works, in short
The RPC server passes incoming network messages directly to cloudpickle loads, so a crafted message executes code when it is deserialised. (Our summary, written by a model. The source text is below.)
Details
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.
References
- https://nvd.nist.gov/vuln/detail/CVE-2024-9053
- https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-222.yaml
- https://github.com/vllm-project/vllm
- https://huntr.com/bounties/75a544f3-34a3-4da0-b5a3-1495cb031e09
Source: GitHub Advisory Database, used under CC BY 4.0.