CVE-2026-54232
CVE-2026-54232 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-427.
Key facts
- Severity: High (CVSS 3.x base score 8.8)
- EPSS exploit prediction: 0% (22nd percentile)
- Actively exploited: Not listed in CISA KEV
- EU (EUVD) id: EUVD-2026-38405
- Weakness: CWE-427
- Affected product: Vllm
- Published:
- Last modified:
Description
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY="unsafe-best-match" is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.
Frequently asked questions
- What is CVE-2026-54232?
- vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulnerable to a dependency confusion attack through the flashinfer-jit-cache package. The package is installed from a custom index (flashinfer.ai/whl/) using --extra-index-url, but the package name was not registered on PyPI, and UV_INDEX_STRATEGY="unsafe-best-match" is set globally. An attacker who registers flashinfer-jit-cache on PyPI with version 0.6.11.post2 can execute arbitrary code as root during the Docker build and backdoor every resulting container image, enabling exfiltration of all user prompts, API credentials, and model data from production vLLM deployments This vulnerability is fixed in 0.22.1.
- How severe is CVE-2026-54232?
- CVE-2026-54232 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-2026-54232 being actively exploited?
- It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (22nd percentile), an estimate of the probability of exploitation in the next 30 days.
- What products are affected by CVE-2026-54232?
- CVE-2026-54232 affects Vllm. See the affected-products list for the exact vulnerable versions.
- How do I fix CVE-2026-54232?
- 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-2026-54232 have an EU (EUVD) identifier?
- Yes. CVE-2026-54232 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2026-38405.
- When was CVE-2026-54232 published?
- CVE-2026-54232 was published on 2026-06-22 and last updated on 2026-06-24.
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…
Other CWE-427 (Uncontrolled Search Path Element) vulnerabilities
- CVE-2025-4981 — Critical (CVSS 9.9): Mattermost versions 10.5.x <= 10.5.5, 9.11.x <= 9.11.15, 10.8.x <= 10.8.0, 10.7.x <= 10.7.2, 10.6.x <= 10.6.5 fail to…
- CVE-2025-69599 — Critical (CVSS 9.8): RayVentory Scan Engine through 12.6 Update 8 allows attackers to gain privileges if they control the value of the PATH…
- CVE-2019-25268 — Critical (CVSS 9.8): NREL BEopt 2.8.0.0 contains a DLL hijacking vulnerability that allows attackers to load arbitrary libraries by tricking…
- CVE-2023-53959 — Critical (CVSS 9.8): FileZilla Client 3.63.1 contains a DLL hijacking vulnerability that allows attackers to execute malicious code by…
- CVE-2025-65741 — Critical (CVSS 9.8): Sublime Text 3 Build 3208 or prior for MacOS is vulnerable to Dylib Injection. An attacker could compile a .dylib file…
- CVE-2024-23054 — Critical (CVSS 9.8): An issue in Plone Docker Official Image 5.2.13 (5221) open-source software that could allow for remote code execution…
Browse all CWE-427 (Uncontrolled Search Path Element) vulnerabilities →