BlackTreeCVE Intelligencevllm-project · vllm
Official source article: GitHub GHSA-7H4P-RFFG-7823 ↗. Check the applicable product and release in the original source.
Medium technical severity with public exploit material referenced by a structured source; prioritise exposed affected systems while verifying vendor guidance.
These OSV and GitHub advisory ranges apply only to the named package and ecosystem. A listed fixed version is not a universal product patch or proof that an update is installed.
| Ecosystem and package | Affected range | First fixed version | Evidence |
|---|---|---|---|
| PyPIvllm | ECOSYSTEM: introduced 0.8.5; fixed 0.24.0 | 0.24.0 | OSV record ↗aggregator derived · 10 Sep 2026 |
| pipvllm | >= 0.8.5, <= 0.23.0 | 0.24.0 | GitHub advisory ↗upstream repository advisory · 17 Jul 2026 |
Structured product status and remediation from the issuing vendor. Product-state explanations are always visible; large lists can be searched or downloaded.
The vendor explicitly identifies these products as affected by this CVE.
Medium technical severity with public exploit material referenced by a structured source; prioritise exposed affected systems while verifying vendor guidance.
Patch availablevLLM 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.
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.
The product receives input that is expected to be of a certain type, but it does not validate or incorrectly validates that the input is actually of the expected type.
An attacker operating through a network path may attempt exploitation without authentication or user interaction. If successful, the issue may disrupt the affected service.
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.
The product receives input that is expected to be of a certain type, but it does not validate or incorrectly validates that the input is actually of the expected type.
An attacker operating through a network path may attempt exploitation without authentication or user interaction. If successful, the issue may disrupt the affected service.
CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.
No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.
A structured CVE source labels at least one public reference as exploit material. BlackTree has not independently validated that it is safe, reliable or weaponised.
CWE-1287: Improper Validation of Specified Type of Input. The product receives input that is expected to be of a certain type, but it does not validate or incorrectly validates that the input is actually of the expected type.
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:L/SC:N/SI:N/SA:NCommon Vulnerability Scoring System 4.0: the compact vector below is decoded into plain language.
Operational remediation based on structured source evidence.
Published 22 Jun 2026 · Last source change 23 Jun 2026, 12:26 UTC · CWE-1287 · Improper Validation of Specified Type of Input
Core structured fields are present and their contributing authorities are shown above.