CVE-2024-9053 json
Remote Code Execution in vllm-project/vllm
published 2025-03-20 19 mo ago modified 2026-08-07 3 mo ago also GHSA-cj47-qj6g-x7r4 , PYSEC-2025-222 , EUVD-2025-6874
- cvss
- 9.8
- version 3.0, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 1.4%
- EPSS 1.4% chance of exploitation in 30 days, percentile 72%
- public exploits
- 0
- none known
Summary
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.
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2024-9053 updated cvss 2.6
vllm: Remote Code Execution in vllm-project/vllm
-
Red Hat Enterprise Linux AI (RHEL AI) rhelai1/bootc-intel-rhel9, rhelai1/instructlab-intel-rhel9affected: workaround, no fix available “Fix deferred”
-
Red Hat Enterprise Linux AI (RHEL AI) rhelai1/ui-rhel9, rhelai1/bootc-amd-rhel9, rhelai1/bootc-nvidia-rhel9, rhelai1/bootc-azure-amd-rhel9, rhelai1/instructlab-amd-rhel9, rhelai1/bootc-aws-nvidia-rhel9, +4 morenot affected: vulnerable code not present
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- total
- Assessed
- 19 mo ago
Exploit prediction
1.38% chance of exploitation in the next 30 days, higher than 72% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- huntr.com https://huntr.com/bounties/75a544f3-34a3-4da0-b5a3-1495cb031e09 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.0 | 9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| NVD | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.0 | 9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | vllm | <=0.6.0 |
no fix listed |
Affected products
- vllm-project vllm-project/vllm
Classification
References
-
huntr.com
/bounties/75a544f3-34a3-4da0-b5a3-1495cb031e09
web, exploit, third-party-advisory, evidence
-
nvd.nist.gov
/vuln/detail/CVE-2024-9053
advisory
-
github.com
/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-222.yaml
web
-
github.com
/vllm-project/vllm
package
-
github.com
/advisories/GHSA-cj47-qj6g-x7r4
advisory
Sources
- CVE List CVE-2024-9053
- GitHub Advisory GHSA-cj47-qj6g-x7r4
- NVD CVE-2024-9053
- OSV PYSEC-2025-222
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.