Improper Validation of Array Index Affecting vllm package, versions [,0.29.0)
Threat Intelligence
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-PYTHON-VLLM-20044392
- published22 Sept 2026
- disclosed18 Sept 2026
- creditUnknown
Introduced: 18 Sep 2026
NewCVE-2026-93840 (opens in a new tab)How to fix?
Upgrade vllm to version 0.29.0 or higher.
Overview
vllm is an A high-throughput and memory-efficient inference and serving engine for LLMs
Affected versions of this package are vulnerable to Improper Validation of Array Index via the stop_token_ids and allowed_token_ids parameters in vllm/sampling_params.py, which are not validated against the model's vocabulary size before being used as column indices into the logits tensor. An attacker can supply out-of-range token IDs in these parameters, causing index operations on the logits tensor to reference positions outside the valid vocabulary range and potentially corrupt inference results.