CVE-2026-56340: vllm Improper Input Validation

Vulnerability summary

CVE-2026-56340 is a high (CVSS 8.8) Improper Input Validation vulnerability in vllm. EPSS estimates a 0.64% chance of exploitation in the next 30 days, higher than 50.1% of scored vulnerabilities.

Timeline

1. 20-06-2026
   PublishedVulnerability first disclosed.
2. 22-07-2026
   Last modifiedVulnerability information updated.

Description

vLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.

• CWE-20Improper Input ValidationThe product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.
• CWE-787Out-of-bounds WriteThe product writes data past the end, or before the beginning, of the intended buffer.