Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
HIGH severity

CVE-2026-22807 vllm

HIGHFix: vllm-project/vllm@78d13ea

CVE-2026-22807 is a high-severity (CVSS 8.8) Code Injection vulnerability in vllm. A fix is available for vllm — see the affected versions and patch details below.

vLLM affected by RCE via auto_map dynamic module loading during model initialization

Also known asGHSA-2pc9-4j83-qjmrPYSEC-2026-2010
Published
Jan 21, 2026
Updated
Aug 12, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Sep 21, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

No confirmed exploitation observed yet

  • A successful exploit gives an attacker total control of the affected component, not partial access.
  • CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-22807.

EPSS Exploitation Probability

via FIRST.org ↗
0.8%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs56th percentile — riskier than 56% of all scored CVEsHighest risk

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

How urgent is this, really

CVE-2026-22807 plotted by exploitation likelihood (EPSS) against impact (CVSS). The shaded corner — EPSS 50%+ and CVSS 7.0+ — is where this CVE doesn't sit, though severity or exploitability alone can still warrant action.

Where this sits among everything scored

Of 377,636 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Real counts from FIRST.org, not a sample — log-scaled since the landscape is heavily right-skewed.

Real-World Exposure

1 pkg affected
🐍vllm

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

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 Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIvllm0.10.1&&< 0.14.00.14.0pip install --upgrade 'vllm==0.14.0'

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for vllm, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.

  2. Fix

    Update vllm to 0.14.0 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-22807 is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 Security's impact-aware SCA analyses which vulnerable code paths your application actually calls, so a match like CVE-2026-22807 can be triaged on real exposure rather than presence alone.

Tailored to CVE-2026-22807. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Fixing This On Your OS

If you run this on a Linux distribution, patch through your package manager against the distro's own security advisory below — it tracks the exact backported fix for your release, which can ship on a different timeline (and sometimes a different severity) than the upstream project.

Red HatImportant

This vulnerability is rated Important for Red Hat as vLLM, an inference and serving engine for large language models, is vulnerable to arbitrary code execution. An attacker influencing the model repository or path can execute malicious Python code during server startup, affecting vLLM versions 0.10.1 through 0.13.x.

ProductFixed inAdvisory
Red Hat AI Inference Server 3.2rhaiis/vllm-cuda-rhel9:1772160593RHSA-2026:3461
Red Hat AI Inference Server 3.2rhaiis/vllm-rocm-rhel9:1772160625RHSA-2026:3462
Red Hat AI Inference Server 3.3rhaiis/vllm-spyre-rhel9:1782352919RHSA-2026:30087
Red Hat AI Inference Server 3.3rhaiis/vllm-rocm-rhel9:1782353093RHSA-2026:30088
Red Hat AI Inference Server 3.3rhaiis/vllm-cuda-rhel9:1782352847RHSA-2026:30089
Red Hat OpenShift AI 2.25rhoai/odh-vllm-cpu-rhel9:1776259063RHSA-2026:10184
Red Hat OpenShift AI 2.25rhoai/odh-vllm-gaudi-rhel9:1772093278RHSA-2026:3782
Red Hat OpenShift AI 2.25rhoai/odh-vllm-cuda-rhel9:1783998774RHSA-2026:42644

Frequently Asked Questions

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
O3 Security · Impact-Aware SCA

Is CVE-2026-22807 in your dependencies?

O3 Security finds CVE-2026-22807 across PyPI dependencies, including transitive ones, and its impact-aware SCA ranks findings by whether your code actually calls the vulnerable path.

CVE-2026-22807: vllm RCE (High 8.8) | O3 Security