CVE-2025-46560: vllm-project vllm

Vulnerability summary

CVE-2025-46560 is a high (CVSS 7.5) vulnerability in vllm-project vllm. EPSS estimates a 0.52% chance of exploitation in the next 30 days, higher than 43.3% of scored vulnerabilities. 1 public exploit is recorded.

Timeline

1. 30-04-2025
   PublishedVulnerability first disclosed.
2. 30-04-2025
   Last modifiedVulnerability information updated.

Description

vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs. Versions starting from 0.8.0 and prior to 0.8.5 are affected by a critical performance vulnerability in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens (e.g., <|audio_|>, <|image_|>) with repeated tokens based on precomputed lengths. Due to ​​inefficient list concatenation operations​​, the algorithm exhibits ​​quadratic time complexity (O(n²))​​, allowing malicious actors to trigger resource exhaustion via specially crafted inputs. This issue has been patched in version 0.8.5.

• CWE-1333Inefficient Regular Expression ComplexityThe product uses a regular expression with a worst-case computational complexity that is inefficient and possibly exponential.