Advisory details:
pypa / vllm/PYSEC-2026-2300
| Advisory ID | pypa/vllm/PYSEC-2026-2300 |
| Aliases |
CVE-2026-41523
GHSA-q8gq-377p-jq3r PYSEC-2026-2300 |
| Summary | 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. |
| Status | Published |
| Exploitability | 0.5 |
| Weighted Severity | 6.8 |
| Risk | 3.4 |
| Affected and Fixed Packages | Package Details |
| Introduced and Fixed Package Commit Patches | Package Commit Patches Details |
| There are no known CWE. |
| System | Score | Found at |
|---|---|---|
| cvssv3.1 | 7.5 | https://github.com/pypa/advisory-database/blob/main/vulns/vllm/PYSEC-2026-2300.yaml |
No EPSS data available for this advisory.
| Patch URL | |
|---|---|
| There are no known patches. | |
| Attack Vector (AV) | Attack Complexity (AC) | Privileges Required (PR) | User Interaction (UI) | Scope (S) | Confidentiality Impact (C) | Integrity Impact (I) | Availability Impact (A) |
|---|---|---|---|---|---|---|---|
network adjacent_network local physical |
low high |
none low high |
none required |
unchanged changed |
high low none |
high low none |
high low none |
Vector: SSVCv2/E:N/A:N/T:T/P:M/B:A/M:M/D:T/2026-06-23T12:23:15Z/
Decision: Track
Source URL: https://github.com/cisagov/vulnrichment/blob/develop/2026/41xxx/CVE-2026-41523.json
Source Advisory: vulnrichment/CVE-2026-41523
[{'Exploitation': 'none'},
{'Automatable': 'no'},
{'Technical Impact': 'total'},
{'Mission Prevalence': 'minimal'},
{'Public Well-being Impact': 'material'},
{'Mission & Well-being': 'medium'}]