vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution
CVE-2026-41523 · GHSA-q8gq-377p-jq3r · published 2026-06-16 · updated 2026-09-03
- Severity
- High
- CVSS score
- 7.5
- Chance of exploitation (EPSS)
- 0.91%
- Fixed in
- 0.22.0
- Exploitation No known exploitation
- Automatable No
- Technical impact Total
- CISA SSVC
Arbitrary code execution. A malicious model author publishes a HuggingFace model with a crafted config.json. When a victim loads this model with vLLM running under python -O or PYTHONOPTIMIZE=1, arbitrary code executes during model initialization with the privileges of the vLLM process. The attack requires: 1. Victim loads a malicious model from HuggingFace (user interaction) 2. vLLM runs under python -O or PYTHONOPTIMIZE=1 (documented in production use) 3. Model uses a cross-encoder architecture (e.g.
Upgrade vllm to 0.22.0 or later. If you start it from an MCP config with npx or uvx, pin that version so an old cached copy is not used.
A fix for this was introduced in this commit: https://github.com/vllm-project/vllm/commit/b3c7ffcab82c2439726f8cb213800f6f38c023d3
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| vllm | PyPI | < 0.22.0 | 0.22.0 |
- CriticalUnauthenticated Remote Code Execution in Langflow via Public Flow Build EndpointlangflowExploited
- CriticalRay is vulnerable to Critical RCE via Safari & Firefox Browsers through DNS Rebinding AttackrayExploited
- CriticalLangflow Unauth RCElangflow, langflow-baseExploited
- HighLiteLLM: Authenticated command execution via MCP stdio test endpointslitellmExploited
- CriticalMLflow vulnerable to remote code execution on unauthenticated servers via third-party scorer deserialization importing caller-placed artifacmlflow
- CriticalAgno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`agno
- CriticalvLLM: OpenAI auth bypassvllm
- CriticalvLLM has RCE In Video Processingvllm
- CriticalvLLM Allows Remote Code Execution via PyNcclPipe Communication Servicevllm
- CriticalvLLM Vulnerable to Remote Code Execution via Mooncake Integrationvllm
- CriticalCVE-2025-24357 Malicious model remote code execution fix bypass with PyTorch < 2.6.0vllm
- CriticalvLLM Deserialization of Untrusted Data vulnerabilityvllm
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.