# CVE-2024-9053: vLLM remote code execution via pickle deserialization in AsyncEngineRPCServer

Source: https://junglewise.ai/threats/cve-2024-9053-vllm-remote-code-execution-via-pickle-deserialization-in  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2025-03-20. Updated: 2026-06-08  
License: CC BY 4.0 with a link back

CVE-2024-9053 · Severity: critical · CVSS 9.8 · Published 2025-03-20

vLLM is a high-performance engine used for serving artificial intelligence models. A security flaw in its remote communication component allows an attacker to execute arbitrary commands on the server hosting the AI model. This could lead to a complete system takeover, theft of proprietary AI models, or unauthorized access to sensitive customer data processed by the engine.

Technologies: [vllm (PyPI)](https://junglewise.ai/threats/technologies/pypi-vllm). Vendors: [PyPI](https://junglewise.ai/threats/vendors/pypi).

## Quick answers

**Is CVE-2024-9053 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2024-9053 being exploited in the wild.

**How severe is CVE-2024-9053?** Critical severity, with a CVSS score of 9.8, published 20 March 2025.

**Which products and versions are affected?** vllm (PyPI) ECOSYSTEM:introduced=0,last_affected=0.6.0.

**Is there a fix for CVE-2024-9053?** No fixed version is recorded yet. Check the vendor's advisory in the references below. If you run it, Junglewise drafts a mitigation that fits your setup and applies it once you approve, with senior security engineers behind it.

**How is CVE-2024-9053 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2024-9053?** Check whether you run vllm (PyPI) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

A deserialization vulnerability exists in vLLM version 0.6.0 and earlier within the AsyncEngineRPCServer component. The vulnerability is located in the run_server_loop() function, which calls _make_handler_coro(). This function utilizes cloudpickle.loads() to process incoming messages without any prior validation or sanitization. An unauthenticated remote attacker can exploit this by sending a specially crafted malicious pickle payload to the RPC server entrypoint, leading to arbitrary code execution with the privileges of the vLLM process. As of the advisory date, no patched version is specified.

## Affected products

- vllm-project vLLM <= 0.6.0

## Identifiers

- CVE-2024-9053
- GHSA-cj47-qj6g-x7r4
- PYSEC-2025-222

## Timeline

- 2025-03-20: disclosed
- 2025-03-20: advisory

## References

- [https://huntr.com/bounties/75a544f3-34a3-4da0-b5a3-1495cb031e09](https://huntr.com/bounties/75a544f3-34a3-4da0-b5a3-1495cb031e09)
- [https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-222.yaml](https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-222.yaml)

## Related threats

- [vLLM chat template resource exhaustion DoS](https://junglewise.ai/threats/cve-2026-115918-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM: Permissive default CORS origins allow cross-origin requests to the vLLM HTTP server](https://junglewise.ai/threats/cve-2026-115917-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM off-by-one error in tokenizer max_token_id validation](https://junglewise.ai/threats/cve-2026-115916-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM image format validation bypass in media processing](https://junglewise.ai/threats/cve-2026-115915-vllm-is-an-inference-and-serving-engine-for-large-language)
- [vLLM denial of service in DeepSeek-OCR image processing](https://junglewise.ai/threats/cve-2026-115914-vllm-is-an-inference-and-serving-engine-for-large-language)