Vulnerability in Vllm
CVE-2025-46560
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.
Vulnerability class: ReDoS (Regular Expression Denial of Service)
Published · last modified .
CVSS v3 metric
CVSS v3 base score 6.5 (Medium). Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H.
EPSS exploit prediction
EPSS: 0.005 (42.2th percentile), scored .
Very low probability of exploitation in the next 30 days; routine patching cadence is appropriate. 42nd percentile — 42.2% of CVEs in the catalogue have a lower EPSS than this one. How to read EPSS.
EPSS over last 30 days · oldest: 0.005 · newest: 0.005 · change: +0.000
Affected products
- Vllm
- Vllm-Project Vllm — versions >= 0.8.0, < 0.8.5
Weakness classification (CWE)
Public proof-of-concept exploits
References
- github.com/vllm-project/vllm/security/advisories/GHSA-vc6m-hm49-g9qg (Exploit, Vendor Advisory)
- github.com/vllm-project/vllm/blob/8cac35ba435906fb7eb07e44fe1a8c26e8744f4e/vllm… (Product)
Frequently asked questions
- What is CVE-2025-46560?
- CVE-2025-46560 is a medium-severity vulnerability in Vllm, classified under Inefficient Regular Expression Complexity. CVSS score: 6.5/10. Published 2025-04-30.
- How severe is CVE-2025-46560?
- Medium severity. CVSS v3 base score is 6.5 out of 10.
- Is CVE-2025-46560 known to be exploited?
- 1 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.