Skip to content
Noroxi
NVD / CVE Program· CNA GitHub_M

CVE-2026-54236: vLLM: incomplete CVE-2026-22778 fix leaks PIL repr addresses via Anthropic router

Noroxi assessment

Priority: Monitor (action score 21/100)

  • A ready-made attack module is public (Nuclei); exploiting it takes no special expertise.
  • Public proof-of-concept code exists (Exploit-DB / GitHub); there is no record of exploitation in the wild.
  • Probability of exploitation in the next 30 days: 0.92% (FIRST EPSS); higher than 60.6% 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 0.23.1rc0.

Low priority for now. Upgrade to vllm-project vllm 0.23.1rc0 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). Prior to 0.23.1rc0, the fix for CVE-2026-22778, which introduced a sanitize_message helper that strips object-repr memory addresses from error messages before they reach the client, is incomplete: several response paths echo str(exc) directly to clients without calling sanitize_message. The unsanitized sites include the Anthropic API router in vllm/entrypoints/anthropic/api_router.py (the POST /v1/messages and POST /v1/messages/count_tokens handlers), the Server-Sent Events streaming converter in vllm/entrypoints/anthropic/serving.py, and the realtime speech-to-text WebSocket in vllm/entrypoints/speech_to_text/realtime/connection.py. These paths catch the exception inside the route coroutine and construct the JSONResponse themselves, bypassing the sanitizing global FastAPI exception handler, and WebSocket frames do not traverse that handler chain at all. Using the same primitive as the parent issue, an unauthenticated attacker can send malformed image bytes through the Anthropic Messages API image content parts so that PIL.Image.open raises an UnidentifiedImageError whose message contains the BytesIO object repr, leaking the heap memory address verbatim in the error.message field of the response body. This vulnerability is fixed in 0.23.1rc0.

MediumCVSS 5.3 · v3.1—Proof of concept Fix available
Published
Jun 22, 2026
Updated
Oct 25, 2026
EPSS
0.9% · 60th percentile

Report tools

JSON

Action score

21

Monitor

Low priority for now.

CVSS
21 / 40 · 5.3 / 10
CISA KEV
0 / 30 · Not listed
EPSS
0 / 30 · 0.9%

CISA SSVC decision

Exploitation
proof of concept
Automatable
yes
Technical impact
partial

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD
—
CNA · GitHub_M
5.3
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
  • Proof of concept exists, no weaponized module
  • A fix has been released

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

Follow CVE-2026-54236

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 vllmbefore 0.23.1

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

    • < 0.23.1rc0affected

Package-level exposure

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

EcosystemPackageAffected rangeFix
PyPIvllmbefore 0.24.00.24.0
PyPIvllmup to and including 0.23.0—

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-2026-54233Jun 22, 2026 · vLLM: OOM Denial of Service via Audio Decompression Bomb
    26Monitor
  • ← EarlierCVE-2026-54235Jun 22, 2026 · vLLM: temperature=NaN and temperature=Infinity bypass validation and propagate to GPU kernels
    27Monitor
  • Later →CVE-2026-55646Jul 6, 2026 · vLLM speech-to-text endpoints allocate full upload before enforcing the audio file-size limit
    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 vllm0.23.1rc0 · descriptionVendor (CNA)
PyPI:vllm0.24.0Package registry (OSV)

Exploit status

Proof of concept available

A public proof of concept or detection signature exists. Exploit knowledge is out there; don't delay patching.

Evidence

  • Nuclei detection template ×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
Nuclei detection templateNuclei template CVE-2026-54236 —

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.

No history yet (it accumulates with the daily EPSS job).

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-2026-22778140 days apartvLLM leaks a heap address when PIL throws an error
    60This week

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
low · data can be read
Integrity
none
Availability
none
Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
None
Scope
Unchanged
Confidentiality impact
Low
Integrity impact
None
Availability impact
None

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:L/I:N/A:N

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 (1 more)

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

All records