Home/CVE/vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid i
CVE

CVE-2026-22778

vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid i

vLLM is an inference and serving engine for large language models (LLMs). From 0.8.3 to before 0.14.1, when an invalid image is sent to vLLM's multimodal endpoint, PIL throws an error. vLLM returns this error to the client, leaking a heap address. With this leak, we reduce ASLR from 4 billion guesses to ~8 guesses.

This vulnerability can be chained a heap overflow with JPEG2000 decoder in OpenCV/FFmpeg to achieve remote code execution. This vulnerability is fixed in 0.14.1.

CRITICAL · CVSS 9.8 EPSS 0.00087
Schedule remediation
  • SSVC automatable: yes - attacks can be scripted at scale
  • CVSS base score ≥ 7.0
Sigma rules0 YARA rules0

Weakness Classification

Affected Products & Versions

1
vllm>= 0.8.3 and < 0.14.1

Affected Packages

1
Language-ecosystem packages (from OSV) tied to this CVE, with the version that fixes it - the dependency-level detail NVD doesn’t carry.
PyPI vllm CRITICAL fixed in 0.14.1

Scoring & Timeline

9.8
CRITICAL · CVSS v3.1 · security-advisories@github.com
View on NVD
Attack Vector
Network Adjacent Local Physical
Attack Complexity
Low High
Privileges Required
None Low High
User Interaction
None Required
Scope
Unchanged Changed
Confidentiality
None Low High
Integrity
None Low High
Availability
None Low High
Published to NVD02 Feb 2026 · 11:16 PM
CVSS VectorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
SSVC triage · cisa-vulnrichment
Exploitation
none
Automatable
yes
Technical impact
total
SSVC asks the questions that actually drive patch urgency: is it being exploited, can attacks be automated, and how total is the impact.

Vendor Advisories

5
rhsaRHSA-2026:19712Important
rhsaRHSA-2026:3462Important
rhsaRHSA-2026:3461Important
rhsaRHSA-2026:3713Important
rhsaRHSA-2026:3782Moderate
🔗

References & Sources

4
Source URLs (vendor pages, mailing lists, write-ups). Exploit/PoC links are in their own section above to avoid duplication.
Intelligence Graph · click any node to traverse
CVETechnique ActorTool Family
drag to reposition · click any node to traverse · button top-right enlarges
External lookups - second-class, for what we don’t hold ourselves
Vulnerabilities
CISA KEV catalog
CWE weaknesses
CAPEC attack patterns
Package vulnerabilities
Threat intelligence
Threat actors
Tools & malware
ATT&CK techniques
IOCs
Detection & defense
Sigma rules
YARA rules
Atomic Red Team tests
D3FEND countermeasures
Compliance
NIST 800-53
ISO 27001:2022
SOC 2 TSC
PCI-DSS v4.0
CIS Controls v8.1
About
All capabilities
Live statistics
Data sources
Privacy policy
Terms of service
threatengine.sh  ·  Open-source threat intelligence platform  ·  100+ authoritative sources  ·  Every fact traces to its origin