CVE-2026-54232

Home/CVE/vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulner

CVE

↯ PDF report

vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.1, the vLLM Dockerfile is vulner

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.

HIGH · CVSS 8.8

Schedule remediation

CVSS base score ≥ 7.0

No Sigma yet — build one → YARA rules0

Look this up elsewhere - one-click external pivots

NVD CVE.org CISA Exploit-DB GitHub PoC VulnCheck KEV GreyNoise

▸ How to read a CVE - triage first, then detect and patch

This page is every public fact about CVE-2026-54232, cross-linked. Its job is to answer one question fast - does this need my attention now? - and then hand you the two things you do about it. Here is how an analyst reads it.

Triage: should I act now? Four signals, and they are not interchangeable:

CVSSseverity - how bad it is IF exploited, 0-10. A high CVSS alone is not urgency; a flaw can be a perfect 10 and never actually be attacked. EPSSprobability - a model’s estimate of the chance it is exploited in the next 30 days, 0-1. This is the “will it actually happen” signal. CISA KEVconfirmed - it is being exploited in the wild right now. The strongest signal on the page; KEV beats any score. Weaponisedavailability - public exploits / PoCs, and especially Metasploit modules rated Excellent / Great. Reliable, packaged exploit code means low-skill attackers can use it today.

How they combine: KEV, or a dependable Metasploit module, means patch now regardless of CVSS. High CVSS + low EPSS + no exploit is real but not an emergency - schedule it. Low CVSS but KEV-listed still gets patched now. The verdict above already weighed these for you; this is how it got there.

Then what - two workflows:

Detectwhen you cannot patch today, follow this CVE to the ATT&CK techniques it enables, then Build a SIEM detection (the green button) - author a rule, test it in Atomic, deploy it. That buys visibility while the patch waits. PatchAffected products / packages tell you if you are exposed; Fixed versions by distribution and Vendor advisories give the exact version that closes it.

Reading order for the panels below: verdict + badges, then Public exploits / Metasploit (is it weaponised), then ATT&CK techniques + Sigma / IDS rules (can I detect it), then Affected products / packages + Fixed versions (am I exposed, what patches it), then Threat actors / IOCs (who uses it), then Scoring & timeline / references (the evidence).

▣

Severity & exploitation scoring

View on NVD →

CVSS base score

8.8

HIGHCVSS v3.1 · [email protected]

EPSS exploitation probability

n/a

No EPSS score in our data for this CVE. EPSS is published daily for scored CVEs - a very new, reserved, or rejected CVE may not have one yet.

CVSS metric silhouette

shape grows toward worst-case

SSVC triage

No SSVC vulnrichment for this CVE. CISA's Vulnrichment program scores newer CVEs (~2024 onwards) plus selected older critical ones. Use the EPSS probability + KEV status to triage instead.

CVSS vector breakdown

Exploitability - how they get in

Attack Vector

Network Adjacent Local Physical

Attack Complexity

Low High

Privileges Required

None Low High

User Interaction

None Required

Scope

Unchanged Changed

Impact - what breaks

Confidentiality

None Low High

Integrity

None Low High

Availability

None Low High

VECTORCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Attack path

Full kill chain

→

◆

ATT&CK techniques

Techniques this CVE enables. Pills with a solid outline are high confidence - named directly in ATT&CK or Nuclei, or human-curated by CTID; the rest are inferred from the weakness type using MITRE's CVE Mapping Methodology and the CWE → CAPEC chain. Broad, generic-weakness guesses are filtered out. A small N× marks a technique that N independent sources agree on.

T1574 · Hijack Execution Flow T1574.001 · DLL T1574.004 · Dylib Hijacking T1574.007 · Path Interception by PATH Environment Variable T1574.008 · Path Interception by Search Order Hijacking T1574.009 · Path Interception by Unquoted Path

▤ Build a SIEM detection for these techniques

▤

CAPEC attack patterns

Attack patterns this CVE enables - the bridge from weakness to ATT&CK technique.

CAPEC-CAPEC-38 · Leveraging/Manipulating Configuration File Search Paths CAPEC-CAPEC-471 · Search Order Hijacking

⬡

Weakness Classification

CWE-427Uncontrolled Search Path Element

▤

Related CVEs

CVEs linked to this one by a shared weakness (CWE) or affected product - joins on data already in the engine, with the reason shown per row. Not a guess.

CVE-2005-0457 Opera 7.54 and earlier on Gentoo Linux uses an insecure path for plugins, which ... same CWE-427 CVE-2013-0725 ERDAS ER Viewer 13.0 has dwmapi.dll and irml.dll libraries arbitrary code execut... same CWE-427 HIGH CVE-2014-8393 DLL Hijacking vulnerability in CorelDRAW X7, Corel Photo-Paint X7, Corel PaintSh... 2 same CWE-427 HIGH CVE-2015-1014 A successful exploit of these vulnerabilities requires the local user to load a ... same CWE-427 HIGH

🔗

References & Sources

Source URLs (vendor pages, mailing lists, write-ups). Exploit/PoC links are in their own section above to avoid duplication.

https://github.com/vllm-project/vllm/security/advisories/GHSA-jrf6-vqxq-pjv2