Advisory details:
vulnrichment / CVE-2026-22807
| Advisory ID | vulnrichment/CVE-2026-22807 |
| Aliases | |
| Summary | vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue. |
| 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 |
|---|---|---|
| cvssv3.1 | 8.8 | |
| ssvc | Track |
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/2026-01-22T15:11:00Z/
Decision: Track
Source URL: https://github.com/cisagov/vulnrichment/blob/develop/2026/22xxx/CVE-2026-22807.json
Source Advisory: vulnrichment/CVE-2026-22807
[{'Exploitation': 'none'},
{'Automatable': 'no'},
{'Technical Impact': 'total'},
{'Mission Prevalence': 'minimal'},
{'Public Well-being Impact': 'material'},
{'Mission & Well-being': 'medium'}]