Is there a public exploit for CVE-2026-126397?

No public exploit for CVE-2026-126397 was found in Exploit-DB, Metasploit, Nuclei templates or public proof-of-concept repositories. That is an absence of evidence rather than proof that none exists.

How severe is CVE-2026-126397?

CVE-2026-126397 scores CVSS 8.7 (v4.0), rated high.

What does CVE-2026-126397 affect?

CVE-2026-126397 affects vllm-project vllm. It is part of the AI and agent stack (vLLM).

8.7 High

vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mmprocessorkwargs.maxpatches value to the Hugging Face processor for Cohere2…

CVE-2026-126397

vLLM from 0.10.1 before 0.31.0 forwards a request-controlled mmprocessorkwargs.maxpatches value to the Hugging Face processor for Cohere2 Vision models without a server-side upper bound, causing quadratic CPU work during multimodal preprocessing. Remote clients can send small image chat-completion requests with large, varying maxpatches values to bypass the LRU cache, exhaust preprocessing workers, and deny service to other clients.

Part of the AI stack

This affects vLLM, in Inference & serving.

Assessment

CVSS: 8.7 (v4.0)
Severity: High
Known exploited: Not listed in CISA KEV
Exploit availability: Nothing found in Exploit-DB, Metasploit, Nuclei or public PoC repositories
Published: 13 November 2026
Last updated: 13 November 2026
Affected: vllm-project · vllm
Assigner: VulnCheck

CVSS vectorCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N

At the source

EUVD (ENISA)

References

Community proofs of concept

No community proof of concept yet. If you have one for a published vulnerability and the right to share it, add it below — it will appear here once reviewed.

Submit a proof of concept

Only for publicly disclosed vulnerabilities, and only material from testing you were authorised to perform. This platform does not buy, sell, or broker exploits — see earning from vulnerability research for legitimate bounty programs. Submissions are reviewed before they appear. Text only; do not include live credentials, personal data, or anything targeting systems you are not permitted to test.

Title *

Proof of concept *

Write-up (optional)

Affected versions (optional)

Name or handle (optional)

References (optional, one URL per line)

Licence for your contribution *

Private contact (optional, never shown)

Before you submit * This vulnerability is already publicly disclosed (it has a published CVE). This material comes only from testing I was authorised to perform. I have the legal right to publish this content and am not breaching any agreement by doing so. It contains no live credentials, personal data, or anything targeting systems I am not authorised to test. I understand it will be reviewed before it appears publicly and may be rejected. I agree to the submission terms.

What is 6 + 7? *

Query this programmatically

Agents can read this through the MCP endpoint, or over HTTP:

curl https://cve.zerocrew.in/api/cve/CVE-2026-126397