vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.18.0, two model implementation files hardcode trust_remote_code=True when loading sub-components, bypassing the user's explicit --trust-remote-code=False security opt-out. This enables remote code execution via malicious model repositories even when the user has explicitly disabled remote code trust. Version 0.18.0 patches the issue.
CVE-2026-27893
“—” beside the score: it is equal to the CVSS score beside it.
Score 8.8 from GitHub Security Advisory (severity: HIGH) published 2026-03-27. The CNA's CVSS baseline 8.8; sources differ by 0.0.
Also known asEUVD-2026-16478 (ENISA EUVD) · GHSA-7972-pg2x-xr59 (GitHub Security Advisories)Source: ENISA EUVD
- High severity, but no confirmed exploitation yet
A fix is available — apply it.
- CVSS v3
- 8.8
- EG Score
- 8.8HIGHmedium confidence
- EG Risk
- 40EG Risk 40/100
EG Risk is EchelonGraph's 0–100 priority score. It fuses impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.
How it’s computed (value × EchelonGraph’s weight)Severity88% × 45%Impact severity (EG Severity): CVSS 8.8 of 10. Never the KEV-floored or EPSS-lifted EG Score.Exploitation1.4% × 40%FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.Automatability0% × 15%CISA's SSVC Automatable value: no (Vulnrichment).SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Track* at high (mission-essential systems).Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.Action: A fix is available. Apply it within your standard update timelines. - EPSS PROB
- 1.4%
- EPSS %ILE
- 71st
- KEV
- Not listed
What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)
The EG score (8.8): severity, escalated by confirmed exploitation. This CVE's 8.8 is its impact severity (EG Severity), not escalated.
- EG Severity
- 8.8 HIGHCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.GitHub Security Advisory CVSS
- EG Likelihood
- 1.4% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-10-31). FIRST's exploitation probability, not an EchelonGraph model.
- Confirmed exploitation
- None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
- EG Priority
- SSVC Track at medium mission impactTrack at low or medium mission impact; Track* at high (mission-essential systems).CISA BOD 26-04: 14 days if the affected system is publicly exposed; Fix on system upgrade if it is not.Each input and its source, and whom BOD 26-04 binds: the SSVC and BOD 26-04 blocks below.
SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Track* at high (mission-essential systems).
A fix is available. Apply it within your standard update timelines.
Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table
BOD 26-04 (CISA's remediation timeline, Table 1)14 days if the affected system is publicly exposed; Fix on system upgrade if it is not.
The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable no (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it
Published
March 27, 2026
Last Modified
July 27, 2026
Advisory Details (10)
Auto-updated Jun 30, 2026Hardcoded trust_remote_code=True in NemotronVL and KimiK25 bypasses user security opt-out · Advisory · vllm-project/vllm · GitHub
https://github.com/vllm-project/vllm/security/advisories/GHSA-7972-pg2x-xr59[Security] Respect user trust_remote_code setting in NemotronVL and KimiK25
Fix merged in vllm-project/vllm PR #36192 on 2026-03-06 — awaiting tagged release
https://github.com/vllm-project/vllm/pull/36192commit 00bd08edeee5 (vllm-project/vllm)
Fix landed in vllm-project/vllm commit 00bd08edeee5 — awaiting tagged release
https://github.com/vllm-project/vllm/commit/00bd08edeee5dd4d4c13277c0114a464011acf72Vendor Advisories for CVE-2026-27893(13)
These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.
- RHSA-2026:73987Red Hat Product SecurityCritical
Red Hat Security Advisory: RHOAI 3.3.7 - Red Hat OpenShift AI
- RHSA-2026:42644Red Hat Product SecurityHigh
Red Hat Security Advisory: RHOAI 2.25.9 - Red Hat OpenShift AI
- RHSA-2026:37275Red Hat Product SecurityCritical
Red Hat Security Advisory: RHOAI 3.3.5 - Red Hat OpenShift AI
- RHSA-2026:24977Red Hat Product SecurityHigh
Red Hat Security Advisory: RHOAI 2.25.7 - Red Hat OpenShift AI
- RHSA-2026:19725Red Hat Product SecurityHigh
Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (ROCm)
- RHSA-2026:19724Red Hat Product SecurityHigh
Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (CUDA)
- RHSA-2026:19712Red Hat Product SecurityCritical
Red Hat Security Advisory: RHOAI 3.3.3 - Red Hat OpenShift AI
- RHSA-2026:10141Red Hat Product SecurityHigh
Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.1
- +5 more
Patch Availability(13)
| Vendor / Ecosystem | Fix (by version range) / Patch | Released | Source |
|---|---|---|---|
| redhat | rhoai/odh-vllm-cpu-rhel9:1790274961 | 2026-09-30 | redhat |
| redhat | rhoai/odh-vllm-rocm-rhel9:1783998857 | 2026-07-21 | redhat |
| redhat | rhoai/odh-vllm-cpu-rhel9:1782996080 | 2026-07-09 | redhat |
| redhat | rhoai/odh-vllm-gaudi-rhel9:1780069069 | 2026-06-10 | redhat |
| redhat | rhoai/odh-vllm-gaudi-rhel9:1778600187 | 2026-05-20 | redhat |
| redhat | rhaiis/vllm-cuda-rhel9:1779223654 | 2026-05-20 | redhat |
| redhat | rhaiis/vllm-rocm-rhel9:1779223651 | 2026-05-20 | redhat |
| redhat | rhelai3/bootc-rocm-rhel9:1776773505 | 2026-04-23 | redhat |
| redhat | rhelai3/disk-image-cuda-rhel9:1776938871 | 2026-04-23 | redhat |
| redhat | rhaiis/vllm-cuda-rhel9:1775680192 | 2026-04-17 | redhat |
| redhat | rhaiis/vllm-rocm-rhel9:1775680262 | 2026-04-17 | redhat |
| redhat | rhaiis/model-opt-cuda-rhel9:1775749857 | 2026-04-17 | redhat |
| pip | vllm @ 0.18.0 (fixes >= 0.10.1, < 0.18.0) | — | ghsa |
Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.
Affected Packages
(1 across 1 ecosystem)
PyPI(1)
| Package | Vulnerable range | Fix by version range | Dependents |
|---|---|---|---|
| vllm | 0.10.1 ... 0.17.1 (15 versions) |
| — |
Weakness Classification(2)
MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.
Data Freshness Timeline
(refreshed 11× in last 7d / 45× in last 30d)
Each row is a time one of our pipelines fetched, updated or re-scored this CVE. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.
Showing the most recent 97 of 173 refreshes on record for this CVE.
A repeat, a row identical to one the same pipeline wrote less than 10 seconds earlier, is not a separate refresh and is not counted. 3 repeat rows among the latest 100 are merged into the row they repeat. The 76 oldest rows on record are not shown and were not checked, so the counts can still include repeats.
- 2026-11-01 16:34 UTCEPSS rescoreEPSS 1.4% · 71st percentile
- 2026-11-01 07:56 UTCGHSA enrichmentGHSA-7972-pg2x-xr59 · GitHub severity HIGH · GitHub CVSS 8.8
- 2026-11-01 07:56 UTCEG score recompute
- 2026-10-31 16:32 UTCEPSS rescoreEPSS 1.4% · 71st percentile
- 2026-10-31 14:18 UTCEG score recompute
- 2026-10-31 14:18 UTCVendor advisory
- 2026-10-30 16:34 UTCEPSS rescoreEPSS 1.4% · 71st percentile
- 2026-10-29 16:33 UTCEPSS rescoreEPSS 1.4% · 71st percentile
- 2026-10-28 16:32 UTCEPSS rescoreEPSS 1.4% · 71st percentile
- 2026-10-27 16:31 UTCEPSS rescoreEPSS 1.4% · 71st percentile
- 2026-10-26 16:31 UTCEPSS rescoreEPSS 1.4% · 71st percentile
- 2026-10-25 16:32 UTCEPSS rescoreEPSS 1.4% · 71st percentile
- 2026-10-25 14:38 UTCEG score recompute
- 2026-10-24 16:32 UTCEPSS rescoreEPSS 1.9% · 79th percentile
- 2026-10-24 15:20 UTCEG score recompute
- 2026-10-24 15:20 UTCVendor advisory
- 2026-10-23 16:31 UTCEPSS rescoreEPSS 1.9% · 79th percentile
- 2026-10-22 16:34 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-21 16:32 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-20 16:32 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-19 16:31 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-18 16:31 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-18 03:50 UTCEG score recompute
- 2026-10-17 16:33 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-17 16:23 UTCEG score recompute
Show 72 moreShow fewer
- 2026-10-17 16:23 UTCVendor advisory
- 2026-10-16 16:41 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-15 16:31 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-14 16:32 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-13 16:34 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-12 16:33 UTCEPSS rescoreEPSS 1.8% · 78th percentile
- 2026-10-12 16:17 UTCEG score recompute
- 2026-10-11 19:59 UTCEG score recompute
- 2026-10-11 17:12 UTCEG score recompute
- 2026-10-11 14:43 UTCEG score recompute
- 2026-10-11 13:48 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-10-11 04:01 UTCOSV refresh
- 2026-10-10 20:00 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-10-09 20:07 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-10-08 17:11 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-10-07 23:47 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-10-06 15:17 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-10-05 17:42 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-10-04 23:21 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-10-03 14:25 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-10-01 19:49 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-09-30 15:03 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-09-28 13:51 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-09-26 15:58 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-09-26 00:26 UTCEPSS rescoreEPSS 1.8% · 77th percentile
- 2026-09-21 16:19 UTCOSV refresh
- 2026-09-18 19:27 UTCEPSS rescoreEPSS 1.3% · 70th percentile
- 2026-09-17 19:30 UTCEPSS rescoreEPSS 1.3% · 70th percentile
- 2026-09-16 14:08 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-16 05:15 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-13 16:47 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-12 15:01 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-11 14:52 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-10 09:34 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-08 22:00 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-07 16:01 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-06 13:47 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-04 05:06 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-02 14:11 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-02 13:14 UTCOSV refresh
- 2026-09-01 13:53 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-09-01 04:39 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-30 19:17 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-30 01:22 UTCEPSS rescoreEPSS 1.3% · 68th percentile
- 2026-08-28 21:41 UTCEPSS rescoreEPSS 1.3% · 68th percentile
- 2026-08-27 14:25 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-26 14:46 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-25 13:48 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-23 00:19 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-21 23:49 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-20 22:55 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-19 17:03 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-18 13:48 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-17 13:47 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-16 14:56 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-16 10:04 UTCEG score recompute
- 2026-08-16 10:04 UTCVendor advisory
- 2026-08-16 02:14 UTCEPSS rescoreEPSS 1.3% · 69th percentile
- 2026-08-15 01:30 UTCEPSS rescoreEPSS 1.3% · 68th percentile
- 2026-08-14 19:15 UTCVendor advisory
- 2026-08-14 06:22 UTCEG score recompute
- 2026-08-14 06:22 UTCVendor advisory
- 2026-08-13 22:00 UTCEPSS rescoreEPSS 1.3% · 68th percentile
- 2026-08-12 20:39 UTCEG score recompute
- 2026-08-12 20:39 UTCVendor advisory
- 2026-08-12 13:50 UTCEPSS rescoreEPSS 1.3% · 68th percentile
- 2026-08-11 20:48 UTCEG score recompute
- 2026-08-11 20:48 UTCVendor advisory
- 2026-08-11 13:42 UTCEPSS rescoreEPSS 1.3% · 68th percentile
- 2026-08-11 03:49 UTCEG score recompute
- 2026-08-11 03:49 UTCVendor advisory
- 2026-08-11 00:00 UTCEPSS rescoreEPSS 1.3% · 68th percentile
Related CVEs(same product + same vendor + same CWE)
Same product
10 shownPyPI:vllm
Same vendor
10 shownredhat:RHSA-2026:10140 · redhat:RHSA-2026:19712 · redhat:RHSA-2026:24977
Frequently asked(5)
What is CVE-2026-27893?
When was the CVE record for CVE-2026-27893 published?
Is CVE-2026-27893 actively exploited?
What is the CVSS score of CVE-2026-27893?
How do I remediate CVE-2026-27893?
Dependency Blast Radius
See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-27893
Is Your Infrastructure Affected by CVE-2026-27893?
EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.