Answer in brief
CVE-2026-41523 records a High severity (CVSS 7.5) vulnerability in vLLM: Security Check Bypass via assert Statement in Activation Function Loading Allows Arbitrary Code Execution. The current sources do not mark it as known exploited. The current feed maps vllm-project/vllm (generic), vllm (pip), vllm (pypi). Check affected ranges and fixed versions before updating.
Analysis pending evidence review
HOL Guard separates source facts from reviewed analysis. See the methodology.
CVSS is 7.5. The current sources do not mark it as known exploited. Treat this as a source-backed prioritization signal, not a statement about your environment.
Analysis status
Analysis pending evidence review
Factual feed record only; HOL analysis is not approved for indexing. Read the methodology.
The current feed maps vllm-project/vllm (generic), vllm (pip), vllm (pypi). Check affected ranges and fixed versions before updating.
| Product | Affected versions | Fixed versions |
|---|---|---|
| cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:* | Not reported | Not reported |
| Package | Affected range | Fixed version |
|---|---|---|
| vllm-project/vllmgeneric | < 0.22.0 | Not reported |
| vllmpip | <0.22.0 | 0.22.0 |
| vllmpypi | >=0 <0.22.0 | 0.22.0 |
Published upstream
Jun 22, 2026
Evidence: source:cvelist:source_dates:source-dates:recordSource modified
Sep 4, 2026
Evidence: source:cvelist:source_dates:source-dates:recordFirst seen by HOL
Jun 19, 2026
vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.22.0, an assert-based security check in vLLM's activation function loading allows any unauthenticated attacker to achieve arbitrary code execution on the server by publishing a malicious HuggingFace model, when vLLM runs in Python optimized mode (python -O or PYTHONOPTIMIZE=1). This vulnerability is fixed in 0.22.0.
Quoted source text, attributed separately from HOL analysis.