Advisory details:
vulnrichment / CVE-2026-54235
| Advisory ID | vulnrichment/CVE-2026-54235 |
| Aliases | |
| Summary | vLLM is an inference and serving engine for large language models (LLMs). Prior to 0.23.1rc0, ll temperature validation gates use comparison operators (<, >), which silently evaluate to False for NaN and for positive Infinity in Python's IEEE 754 float semantics. Both values pass every guard and propagate to GPU sampling kernels, where they produce undefined behavior or CUDA errors that can crash the inference worker. This vulnerability is fixed in 0.23.1rc0. |
| Status | Published |
| Exploitability | 0.5 |
| Weighted Severity | 0.0 |
| Risk | |
| Affected and Fixed Packages | Package Details |
| Introduced and Fixed Package Commit Patches | Package Commit Patches Details |
| System | Score | Found at |
|---|---|---|
| cvssv4 | 6.9 | |
| ssvc | Track |
No EPSS data available for this advisory.
| Patch URL | |
|---|---|
| There are no known patches. | |
| Attack Vector (AV) | Attack Complexity (AC) | Attack Requirements (AT) | Privileges Required (PR) | User Interaction (UI) | Vulnerable System Impact Confidentiality (VC) | Vulnerable System Impact Integrity (VI) | Vulnerable System Impact Availability (VA) | Subsequent System Impact Confidentiality (SC) | Subsequent System Impact Integrity (SI) | Subsequent System Impact Availability (SA) |
|---|---|---|---|---|---|---|---|---|---|---|
network adjacent local physical |
low high |
none present |
none low high |
none passive active |
high low none |
high low none |
high low none |
high low none |
high low none |
high low none |
Vector: SSVCv2/E:N/A:Y/T:P/P:M/B:A/M:M/D:T/2026-06-23T12:25:28Z/
Decision: Track
Source URL: https://github.com/cisagov/vulnrichment/blob/develop/2026/54xxx/CVE-2026-54235.json
Source Advisory: vulnrichment/CVE-2026-54235
[{'Exploitation': 'none'},
{'Automatable': 'yes'},
{'Technical Impact': 'partial'},
{'Mission Prevalence': 'minimal'},
{'Public Well-being Impact': 'material'},
{'Mission & Well-being': 'medium'}]