How severe is CVE-2026-22778?

CVE-2026-22778 has a CVSS 3.x base score of 9.8, rated critical severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is high, integrity high, and availability high.

Is CVE-2026-22778 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 4% (89th percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2026-22778?

CVE-2026-22778 affects Vllm. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2026-22778?

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

Does CVE-2026-22778 have an EU (EUVD) identifier?

Yes. CVE-2026-22778 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-5277.

When was CVE-2026-22778 published?

CVE-2026-22778 was published on 2026-02-02 and last updated on 2026-06-29.

CVE-2026-22778

CVE-2026-22778 is a critical-severity vulnerability in Vllm with a CVSS 3.x base score of 9.8. 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-532.

Key facts

Severity: Critical (CVSS 3.x base score 9.8)
EPSS exploit prediction: 4% (89th percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2026-5277
Weakness: CWE-532
Affected product: Vllm
Published: 2026-02-02
Last modified: 2026-06-29

Description

vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.

Frequently asked questions

What is CVE-2026-22778?: vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses. This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.
How severe is CVE-2026-22778?: CVE-2026-22778 has a CVSS 3.x base score of 9.8, rated critical severity. It is exploitable over network with low attack complexity, requires no privileges and no user interaction. Impact on confidentiality is high, integrity high, and availability high.
Is CVE-2026-22778 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 4% (89th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2026-22778?: CVE-2026-22778 affects Vllm. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2026-22778?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its critical severity, prioritise patching exposed systems.
Does CVE-2026-22778 have an EU (EUVD) identifier?: Yes. CVE-2026-22778 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-5277.
When was CVE-2026-22778 published?: CVE-2026-22778 was published on 2026-02-02 and last updated on 2026-06-29.

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-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…
CVE-2026-54232 — High (CVSS 8.8): vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is…

All CVEs affecting Vllm →

Other CWE-532 (Insertion of Sensitive Information into Log File) vulnerabilities

CVE-2022-36407 — Critical (CVSS 9.9): Insertion of Sensitive Information into Log File vulnerability in Hitachi Virtual Storage Platform, Hitachi Virtual…
CVE-2023-40029 — Critical (CVSS 9.9): Argo CD is a declarative continuous deployment for Kubernetes. Argo CD Cluster secrets might be managed declaratively…
CVE-2021-32724 — Critical (CVSS 9.9): check-spelling is a github action which provides CI spell checking. In affected versions and for a repository with the…
CVE-2026-49200 — Critical (CVSS 9.8): The acer_cgi.log file in the device firmware is accessible without authentication via the web interface. This file…
CVE-2025-11008 — Critical (CVSS 9.8): The CE21 Suite plugin for WordPress is vulnerable to Sensitive Information Exposure in all versions up to, and…
CVE-2024-52009 — Critical (CVSS 9.8): Atlantis is a self-hosted golang application that listens for Terraform pull request events via webhooks. Atlantis logs…

Browse all CWE-532 (Insertion of Sensitive Information into Log File) vulnerabilities →