CVE-2026-22807

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.

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

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.

Untrusted input is evaluated as executable code within the application's runtime environment. Typical impact: arbitrary code execution within the application's privilege context.

CVE-2026-22807 has a CVSS score of 8.8 (High). The vector is network-reachable, no privileges required, and user interaction required. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.14.0); upgrading removes the vulnerable code path.

Kodem intelligence

1. What is CVE-2026-22807? CVE-2026-22807 is a high-severity code injection vulnerability in vllm (pip), affecting versions >= 0.10.1, < 0.14.0. It is fixed in 0.14.0. Untrusted input is evaluated as executable code within the application's runtime environment.
2. How severe is CVE-2026-22807? CVE-2026-22807 has a CVSS score of 8.8 (High). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
3. Which versions of vllm are affected by CVE-2026-22807? vllm (pip) versions >= 0.10.1, < 0.14.0 is affected.
4. Is there a fix for CVE-2026-22807? Yes. CVE-2026-22807 is fixed in 0.14.0. Upgrade to this version or later.
5. Is CVE-2026-22807 exploitable, and should I be worried? Whether CVE-2026-22807 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
6. What actually determines whether CVE-2026-22807 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
7. How do I fix CVE-2026-22807? Upgrade vllm to 0.14.0 or later.