Skip to content
Noroxi
NVD / CVE Program· CNA GitHub_M

CVE-2026-44222: vLLM: Remote DoS via Special-Token Placeholders

HighCVSS 7.5 · v3.1—No exploit Fix available

Noroxi assessment

Priority: Monitor (action score 30/100)

  • The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
  • Probability of exploitation in the next 30 days: 0.41% (FIRST EPSS).
  • Anyone who can reach it over the internet can trigger it. No account or password is required. No user action is required. No special conditions are required; it is repeatable.
  • Fixed version: vllm-project vllm 0.20.0.

Low priority for now. Upgrade to vllm-project vllm 0.20.0 or later.

Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it

Primary sources: NVD · CVE.org · FIRST EPSS

vLLM is an inference and serving engine for large language models (LLMs). From 0.6.1 to before 0.20.0, there is a a Token Injection vulnerability in vLLM’s multimodal processing. Unauthenticated, text-only prompts that spell special tokens are interpreted as control. Image and video placeholder sequences supplied without matching data cause vLLM to index into empty grids during input-position computation, raising an unhandled IndexError and terminating the worker or degrading availability. Multimodal paths that rely on image_grid_thw/video_grid_thw are affected. This vulnerability is fixed in 0.20.0.

Published
May 12, 2026
Updated
Nov 11, 2026
EPSS
0.4% · 36th percentile

Report tools

JSON

Action score

30

Monitor

Low priority for now.

CVSS
30 / 40 · 7.5 / 10
CISA KEV
0 / 30 · Not listed
EPSS
0 / 30 · 0.4%

CISA SSVC decision

Exploitation
none
Automatable
no
Technical impact
partial

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD
7.5
CNA · GitHub_M
6.5
1.0 point gap

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

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Get told when this record changes

  • Not in KEV: no record of exploitation in the wild
  • No public exploit code on record
  • A fix has been released

If any of these changes, we'll tell you in the daily email digest.

Follow CVE-2026-44222

When you'll hear from us

  • when it enters CISA KEV
  • when exploit code appears or is weaponized
  • when the record is updated (including a fixed version)
  • when EPSS rises 20 points in a week

One daily email digest (06:00 UTC); connect a webhook for KEV listings and weaponized exploits every 10 minutes on paid plans, on the hour on the free plan.

Your free account also gets you

  • CVE alerts: add the products and versions you run, get the new CVEs that affect them
  • Uptime monitoring: 1 site, instant email when it goes down
  • Add your domain: subdomains and takeover risk scanned every week (1 domain)
  • 10 scans an hour on the security tools, at most 30 a day (3 a day without an account), an API key and MCP
  • All your scans in one panel: findings, what changed in the last scan, a report per domain or per client (PDF, share link)
All free tools

Sign up with email · Have an account? Sign in

Free account, no card. Unfollow any time.

Don't want an account? Get "Exploited this week" by email every MondayDon't want an account? RSS feed for vllm records
Is your version affected? Check it

Noroxi analysis

What does it mean in your environment?

The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.

We use this product, ask for help

Affected systems

Is your version affected?

Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.

VendorProduct
vllmvllm

Versions reported by the vendor

Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.

  • vllm-project vllm

    • >= 0.6.1, < 0.20.0affected

Affected versions

NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.

  • vllm vllm0.6.1 and later · before 0.20.0

Package-level exposure

OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.

EcosystemPackageAffected rangeFix
PyPIvllmfrom 0.6.1 · before 0.20.00.20.0

Same product

vllm: all records

Other highest-scoring records for the same primary product.

  • CVE-2026-22778vLLM leaks a heap address when PIL throws an error
    60This week
  • CVE-2025-32444vLLM Vulnerable to Remote Code Execution via Mooncake Integration
    40Plan
  • CVE-2024-11041Remote Code Execution in vllm-project/vllm
    40Plan

Published before and after this one in the same product

  • ← EarlierCVE-2026-34756Apr 6, 2026 · vLLM Affected by Unauthenticated OOM Denial of Service via Unbounded `n` Parameter in OpenAI API Server
    26Monitor
  • ← EarlierCVE-2026-7141Apr 27, 2026 · vLLM KV Block kv_cache_interface.py has_mamba_layers uninitialized resource
    11Monitor
  • Later →CVE-2026-44223May 12, 2026 · vLLM: extract_hidden_states speculative decoding crashes server on any request with penalty parameters
    26Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

Product / packageFixed versionSource
vllm-project vllm0.20.0 · descriptionVendor (CNA)
PyPI:vllm0.20.0Package registry (OSV)

Exploit status

No known public exploit

No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

No dated events beyond publication.

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

  • CVE-2026-93592129 days apartvLLM before 0.28.0 Denial of Service via negative token ID
    34Monitor
  • CVE-2025-62372172 days apartvLLM vulnerable to DoS with incorrect shape of multimodal embedding inputs
    33Monitor
  • CVE-2026-100654137 days apartvLLM before 0.29.0 Denial of Service via out-of-range stop_token_ids
    28Monitor
  • CVE-2026-116181166 days apartvLLM 0.20.1 before 0.29.0 DoS and GPU Out-of-Bounds Write via stop_token_ids
    28Monitor
  • CVE-2026-115916167 days apartvLLM: Out-of-vocabulary prompt token id passes input validation and triggers a CUDA device-side assert (engine crash / DoS)
    26Monitor
  • CVE-2026-93841129 days apartvLLM through 0.29.0 Adjacent-Request Sampler State Corruption via Unvalidated Prompt Token IDs
    25Monitor

Not on record for this CVE: EPSS history · patch commit or PR link · researcher credit · public bounty program.

Technical details

Attack conditions

  • Anyone who can reach it over the internet can trigger it.
  • No account or password is required.
  • No user action is required.
  • No special conditions are required; it is repeatable.

If successful

Confidentiality
none
Integrity
none
Availability
high · the service can be disrupted
Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
None
Scope
Unchanged
Confidentiality impact
None
Integrity impact
None
Availability impact
High

Weakness class (CWE)

CWE-129 · Improper Validation of Array Index

CVSS vector

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

nvd-primary

Attack context

MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.

ATT&CK techniques

—

References

Vendor advisories and official records. Exploit/PoC links are deliberately left out.

All records