CVE-2025-46560

CVSS v3 Score
7.5
High

Vulnerability 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.

CVSS:7.5(High)

A vulnerability was found in markdown-it up to 2.x. It has been classified as problematic. Affected is an unknown function of the file lib/common/html_re.js. The manipulation leads to inefficient regu...

CVSS:7.5(High)

The ms package before 0.7.1 for Node.js allows attackers to cause a denial of service (CPU consumption) via a long version string, aka a "regular expression denial of service (ReDoS)."

CVSS:7.5(High)

The marked package before 0.3.4 for Node.js allows attackers to cause a denial of service (CPU consumption) via unspecified vectors that trigger a "catastrophic backtracking issue for the em inline ru...

CVSS:7.5(High)

A vulnerability classified as problematic has been found in debug-js debug up to 3.0.x. This affects the function useColors of the file src/node.js. The manipulation of the argument str leads to ineff...

CVSS:7.5(High)

A vulnerability was found in email-existence. It has been rated as problematic. Affected by this issue is some unknown functionality of the file index.js. The manipulation leads to inefficient regular...

CVSS:7.5(High)

A vulnerability was found in rgb2hex up to 0.1.5. It has been rated as problematic. This issue affects some unknown processing. The manipulation leads to inefficient regular expression complexity. The...