How severe is CVE-2026-22807?

CVE-2026-22807 has a CVSS score of 8.8/10, rated HIGH. Immediate patching is strongly recommended.

Which packages are affected by CVE-2026-22807?

CVE-2026-22807 affects the following packages: vllm (PyPI). Ecosystems affected: PyPI.

How do I fix CVE-2026-22807?

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.

How do I detect CVE-2026-22807 in my PyPI dependencies?

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.

How do I mitigate CVE-2026-22807 if there is no patch (or I can't update yet)?

Stop passing untrusted input into the interpreter or shell: call the affected binary with an argument array rather than a composed command string, reject anything outside a strict allowlist of expected values, and run the component under an account that cannot reach beyond the work it legitimately does.

Is CVE-2026-22807 actively exploited in the wild?

No public exploit code has been indexed for CVE-2026-22807 yet. This does not mean the vulnerability cannot be exploited — absence of public exploits does not imply safety. Apply the recommended fix and use O3 Security to monitor your exposure.

What is the EPSS score for CVE-2026-22807?

CVE-2026-22807 has an EPSS (Exploit Prediction Scoring System) score of 1.0%, placing it in the 62th percentile of all CVEs. EPSS is maintained by FIRST.org and estimates the probability that a vulnerability will be exploited in the wild within the next 30 days. This score indicates relatively lower exploitation probability, though the CVSS severity should still guide your patching priority.

What type of vulnerability is CVE-2026-22807?

CVE-2026-22807 is classified as Code Injection (CWE-94). This weakness type describe the underlying flaw category, which helps determine the potential impact and the right class of mitigation. This is a high-impact weakness class that often enables remote code execution or data exposure.

When was CVE-2026-22807 published, and has it been updated?

CVE-2026-22807 was published on January 21, 2026 and was last updated on October 28, 2026. Advisory data evolves as severity scores, affected ranges, and exploit intelligence are revised — always check the latest version of the advisory before acting.

🐍

🐍 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

Oct 28, 2026

Affected

1 pkg

Patched

1 / 1

Exploits

None indexed

Exploitation data as of Nov 6, 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 ↗

1.0%probability of exploitation in next 30 days

Lower Risk0.00%

Lower risk than most CVEs62th percentile — riskier than 62% of all scored CVEsHighest risk

Probability of exploitation in the next 30 days, from FIRST.org EPSS.

How urgent is this, really

Where this sits among everything scored

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

Summary

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.

Impact

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.

Affected Versions

All versions where vllm/model_executor/models/registry.py resolves auto_map entries with try_get_class_from_dynamic_module without checking trust_remote_code (at least current main).

Details

During model resolution, vLLM unconditionally iterates auto_map entries from the model config and calls try_get_class_from_dynamic_module, which delegates to Transformers’ get_class_from_dynamic_module and executes the module code.

This occurs even when trust_remote_code is false, allowing a malicious model repo to embed code in a referenced module and have it executed during initialization.

Relevant code

vllm/model_executor/models/registry.py:856 — auto_map resolution
vllm/transformers_utils/dynamic_module.py:13 — delegates to get_class_from_dynamic_module, which executes code

Fixes

https://github.com/vllm-project/vllm/pull/32194

Credits

Reported by bugbunny.ai

Affected Packages

1 total 1 fixed

Ecosystem	Package	Vulnerable range	Fix
🐍PyPI	`vllm`	≥ 0.10.1&&< 0.14.0	0.14.0`pip install --upgrade 'vllm==0.14.0'`

Affected Products

1 product · 1 configurations

Application

vllmvllm

≥ 0.10.1 && < 0.14.0

range

Detection & mitigation playbook

Open-source dependency

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.
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.
Workarounds
Stop passing untrusted input into the interpreter or shell: call the affected binary with an argument array rather than a composed command string, reject anything outside a strict allowlist of expected values, and run the component under an account that cannot reach beyond the work it legitimately does.

Frequently Asked Questions

# Summary 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. --- # Impact 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**. --- # Affected Versions All versions where `vllm/model_executor/models/registry.py` resolves `auto_map`

O3 Security · Impact-Aware SCA

Is CVE-2026-22807 in your dependencies?

Find it across PyPI, including transitive dependencies.

Scan my dependencies How O3 SCA works