Skip to content
Noroxi
NVD / CVE Program· CNA GitHub_M

CVE-2026-22778: vLLM leaks a heap address when PIL throws an error

Noroxi assessment

Priority: This week (action score 60/100)

  • A ready-made attack module is public (Metasploit, Nuclei); exploiting it takes no special expertise.
  • A ready-made attack tool exists and the flaw can be exploited over the network without an account, so priority is at least “This week”.
  • Probability of exploitation in the next 30 days: 18.2% (FIRST EPSS); higher than 97.2% of all records.
  • 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.
  • According to CISA the attack is automatable: targets can be found by mass scanning.
  • Fixed version: vllm-project vllm 0.14.1.

Don’t wait for the next maintenance window. Upgrade to vllm-project vllm 0.14.1 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 0.8.3 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.

CriticalCVSS 9.8 · v3.1—Weaponized Fix available
Published
Feb 2, 2026
Updated
Jul 15, 2026
EPSS
18.2% · 97th percentile

Report tools

JSON

Action score

60

This week

Don’t wait for the next maintenance window.

CVSS
39 / 40 · 9.8 / 10
CISA KEV
0 / 30 · Not listed
EPSS
5 / 30 · 18.2%
Ready-made attack tool
16 / 60 · floor: at least 60

CISA SSVC decision

Exploitation
none
Automatable
yes
Technical impact
total

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD
—
CNA · GitHub_M
9.8
NVD has not scored this yet; the score shown is the CNA’s.

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
  • Weaponized exploit exists
  • A fix has been released

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

Follow CVE-2026-22778

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 instantly.

Your free account also gets you

Running WordPress? Scan your site free with WP Lens

  • Stack 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 (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

Running WordPress? Scan your site free with WP Lens

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

Affected versions

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

  • vllm vllm0.8.3 and later · before 0.14.1

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

    • >= 0.8.3, < 0.14.1affected

Package-level exposure

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

EcosystemPackageAffected rangeFix
PyPIvllmfrom 0.8.3 · before 0.14.10.14.1

Same product

vllm: all records

Other highest-scoring records for the same primary product.

  • CVE-2025-32444vLLM Vulnerable to Remote Code Execution via Mooncake Integration
    40Plan
  • CVE-2024-11041Remote Code Execution in vllm-project/vllm
    40Plan
  • CVE-2026-115915vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
    39Monitor

Published before and after this one in the same product

  • ← EarlierCVE-2026-22807Jan 21, 2026 · vLLM affected by RCE via auto_map dynamic module loading during model initialization
    39Monitor
  • ← EarlierCVE-2026-24779Jan 27, 2026 · vLLM vulnerable to Server-Side Request Forgery (SSRF) in `MediaConnector`
    28Monitor
  • Later →CVE-2026-25960Mar 9, 2026 · SSRF Protection Bypass in vLLM
    39Monitor

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 vllm0.14.1 · descriptionVendor (CNA)
PyPI:vllm0.14.1Package registry (OSV)

Exploit status

Weaponized

A ready exploit tool or active in-the-wild use is known for this vulnerability. This should be your top priority.

Evidence

  • Metasploit module ×1
  • Nuclei detection template ×2
  • Proof-of-concept repository on GitHub ×1

Noroxi does not host or link to exploit code. Metasploit module names and Nuclei template ids are shown (names, not code); Exploit-DB entries and PoC repositories are given as counts only.

Public exploit evidence
SourceKindDate
Metasploit moduleauxiliary/scanner/http/vllm_multimodal_info_leakvLLM Multimodal Heap-Address Information Leak Scannerauxiliary2026-02-02
Nuclei detection templateNuclei template CVE-2026-22778 —
Nuclei detection templateNuclei template CVE-2026-54236 —
Proof-of-concept repository on GitHubstars:02026-09-05

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.

  1. Metasploit-1 d
  2. Published
  3. First PoC+214 d
  4. TodayOct 31, 2026+271 d
EPSS, last 120 days+2% in 7 days

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

Credits

All researchers

Finders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.

No credits in the CNA record.

Variant candidates

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

  • CVE-2026-54236140 days apartvLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router
    21Monitor

Chain candidates

An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.

—

Bug bounty scope

No known public program.

Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).

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

Weakness class (CWE)

CWE-532 · Insertion of Sensitive Information into Log File

CVSS vector

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

nvd-secondary

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

—

Change log

  1. Fix✗ → ✓

For records you follow, these changes also arrive as notifications. →

References

Show all references (14 more)

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

All records