How severe is CVE-2026-22807?

CVE-2026-22807 has a CVSS 3.x base score of 8.8, rated high severity. It is exploitable over network with low attack complexity, requires no privileges and user interaction. Impact on confidentiality is high, integrity high, and availability high.

Is CVE-2026-22807 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 1% (50th percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2026-22807?

CVE-2026-22807 affects Vllm. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2026-22807?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.

Does CVE-2026-22807 have an EU (EUVD) identifier?

Yes. CVE-2026-22807 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-3678.

When was CVE-2026-22807 published?

CVE-2026-22807 was published on 2026-01-21 and last updated on 2026-06-30.

CVE-2026-22807

CVE-2026-22807 is a high-severity vulnerability in Vllm with a CVSS 3.x base score of 8.8. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-94.

Key facts

Severity: High (CVSS 3.x base score 8.8)
EPSS exploit prediction: 1% (50th percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2026-3678
Weakness: CWE-94
Affected product: Vllm
Published: 2026-01-21
Last modified: 2026-06-30

Description

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.

Frequently asked questions

What is CVE-2026-22807?: vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.
How severe is CVE-2026-22807?: CVE-2026-22807 has a CVSS 3.x base score of 8.8, rated high severity. It is exploitable over network with low attack complexity, requires no privileges and user interaction. Impact on confidentiality is high, integrity high, and availability high.
Is CVE-2026-22807 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 1% (50th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2026-22807?: CVE-2026-22807 affects Vllm. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2026-22807?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
Does CVE-2026-22807 have an EU (EUVD) identifier?: Yes. CVE-2026-22807 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-3678.
When was CVE-2026-22807 published?: CVE-2026-22807 was published on 2026-01-21 and last updated on 2026-06-30.

References

Affected products (1)

cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*

More vulnerabilities in Vllm

CVE-2025-32444 — Critical (CVSS 10.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.6.5 and…
CVE-2026-22778 — Critical (CVSS 9.8): vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid…
CVE-2025-47277 — Critical (CVSS 9.8): vLLM, an inference and serving engine for large language models (LLMs), has an issue in versions 0.6.5 through 0.8.4…
CVE-2024-11041 — Critical (CVSS 9.8): vllm-project vllm version v0.6.2 contains a vulnerability in the MessageQueue.dequeue() API function. The function uses…
CVE-2026-48746 — Critical (CVSS 9.1): vLLM is an inference and serving engine for large language models (LLMs). From 0.3.0 until 0.22.0, a vulnerability in…
CVE-2025-29783 — Critical (CVSS 9.0): vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. When vLLM is configured to use…

All CVEs affecting Vllm →

Other CWE-94 (Code Injection) vulnerabilities

CVE-2026-57624 — Critical (CVSS 10.0): Unauthenticated Remote Code Execution (RCE) in Blocksy Companion Pro <= 2.1.46 versions.
CVE-2026-10134 — Critical (CVSS 10.0): IBM Langflow OSS 1.0.0 through 1.9.3 allows an attacker to read every secret available to the Langflow process, read…
CVE-2026-53576 — Critical (CVSS 10.0): Kestra is an open-source, event-driven orchestration platform. Prior to 1.0.45 and 1.3.21, the authentication filter…
CVE-2026-10561 — Critical (CVSS 10.0): IBM Langflow OSS 1.0.0 through 1.9.3 has an vulnerability due to an improper isolation of Python execution combined…
CVE-2026-25470 — Critical (CVSS 10.0): Improper Control of Generation of Code ('Code Injection') vulnerability in ACPT ACPT (Pro) - Custom Post Types Plugin…
CVE-2026-48836 — Critical (CVSS 10.0): Unauthenticated Remote Code Execution (RCE) in Easy Invoice <= 2.1.19 versions.

Browse all CWE-94 (Code Injection) vulnerabilities →