CVE-2026-228078.8HighCWE-94

CVE-2026-22807: vLLM affected by RCE via auto_map dynamic module loading during model initialization

vllm-project · vllm

Vendor fix available · Affected: vllm-project · Exploitation: unlikely (under 1%)

Not in CyberSIXT coverage yet: no article names this CVE. This page shows the public record.

1.0%probability of exploitation in the next 30 days

62nd percentile

050100

Higher than 62% of scored CVEs

8.8HighCVSS 3.1

LowMediumHighCrit.

DescriptionCVE.org

vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.

Affected products1

From the CVE record. A product or version that is not listed is unknown, not unaffected.

vllm-project · vllm>= 0.10.1, < 0.14.0

On the Atlas

Every published CVE is on the CyberSIXT Atlas, grouped by weakness, vendor and month.

Open the Atlas

Exploitation: Unlikely (under 1%). EPSS under 1%, or no score yet.
CISA KEV: Not listed
Public check: No public nuclei template
Weakness: Code Injection · Command and Code Injection
Vendor: vllm-project
Published: January 2026
Band: Unlikely (under 1%), January 2026

CoverageNo articles yet

No CyberSIXT article names CVE-2026-22807 yet, so there is no coverage timeline, action brief or change log for it. Everything on this page comes from the public CVE record, CISA KEV, EPSS and the nuclei template index. Search the archive or see the CVEs in the news.

References

5 more references are in the CVE record.