nday
CVE-2026-54232 GHSA-jrf6-vqxq-pjv2

vLLM: Dependency Confusion Vulnerability in vLLM Dockerfile

vllm-project / vllm

CVE 공개: . nday가 아직 패치 근거를 수집하지 않았습니다. 패치가 없다는 뜻은 아닙니다. PoC 출처 4곳 모두 미등재. CISA KEV 미등재.

tags weakness typeuncontrolled search path accessnetworkno authentication required productvLLM product typeAI / ML
why these tags

nday derives these tags by fixed rules from the facts below; NVD, the CNA and other sources do not assign them. Vocabulary and rules: ~/tags.

uncontrolled search path
CWE-427, stated by the CNA GitHub_M 및 NVD, republishing [email protected]
network
AV:N in CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H (CVSS 3.1) from the CNA GitHub_M
no authentication required
PR:N in CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H (CVSS 3.1) from the CNA GitHub_M
vLLM
affected products in the CVE record: vllm-project · vllmCPE names NVD's analysts give as vulnerable: a:vllm:vllm
AI / ML
affected products in the CVE record: vllm-project · vllmCPE names NVD's analysts give as vulnerable: a:vllm:vllmthe product type of vLLM in nday's product registry
현재 단계
DIS
공개
CVSS
8.8 HIGH v3.1

생명주기

가로축 UTC. 점 = 분 단위, 넓은 막대 = 날짜만, 빈 표시 = 불명 또는 추정.
시점 알 수 없음
DIS공개
06-22T22:16Z
PAT패치
아직 기록 없음
ANA분석
아직 기록 없음
POCPoC
아직 기록 없음
ITW악용
아직 기록 없음
KEVKEV
아직 기록 없음

요약

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.

Original text of the CVE record (cvelist), shown as published.

Exploit conditions

What an attack needs, read from the CVSS vector.
Attack vector AV:N
Network: the attacker only needs to reach it over the network
Attack complexity AC:L
Low: no special conditions; the attacker can expect repeatable success
Privileges required PR:N
None: no account or authorization needed
User interaction UI:R
Required: a user must do something, such as open a file or click a link

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

CVSS 3.1 vector from the CVE record, scored by the CNA GitHub_M.

이벤트 로그

+DISCVE 공개

CVE 레코드 공개(CNA: GitHub_M). CVSS 8.8(높음).

출처 cvelist · nday 일괄 수집 · 원본
{
  "id": 430881,
  "type": "disclosed",
  "source": "cvelist",
  "url": "https://www.cve.org/CVERecord?id=CVE-2026-54232",
  "occurred_at": "2026-06-22T22:16:43.101Z",
  "observed_at": "2026-11-13T05:39:55.731897Z",
  "is_backfill": true,
  "dedupe_key": "",
  "detail": {
    "cvss": {
      "source": "cna",
      "vector": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
      "version": "3.1",
      "base_score": 8.8,
      "base_severity": "HIGH"
    },
    "ssvc": {
      "timestamp": "2026-06-23T14:29:54.064861Z",
      "automatable": "no",
      "exploitation": "none",
      "technical_impact": "total"
    },
    "state": "PUBLISHED",
    "date_published": "2026-06-22T22:16:43.101Z",
    "assigner_short_name": "GitHub_M"
  }
}

Report an error

report an error or omission

Something on this page wrong or missing? Tell the editors; if they accept it, this page's revision log says so publicly. Upstream data is not changed.

연구자 논의

최근 7일간 연구자 0명이 언급

목록의 연구자가 X에서 이 CVE를 언급한 게시물입니다. 원문 그대로 보여 주며 nday는 검증하지 않습니다.

명단의 연구자가 X에서 이 CVE를 언급한 게시물은 아직 수집되지 않았습니다.

Discussion

0 comments

No comments yet.