| Component | vLLM |
| Severity | medium (CVSS 6.5) |
| CVSS vector | CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H |
| Published (NVD) | 2025-05-30 |
| Last modified | 2026-06-17 |
| Affected versions | vllm >= 0.6.4, < 0.9.0 |
| Fixed in | 0.9.0 |
| Weakness | CWE-1333 |
| CISA KEV | not listed |
NVD description
vLLM, an inference and serving engine for large language models (LLMs), has a Regular Expression Denial of Service (ReDoS) vulnerability in the file `vllm/entrypoints/openai/tool_parsers/pythonic_tool_parser.py` of versions 0.6.4 up to but excluding 0.9.0. The root cause is the use of a highly complex and nested regular expression for tool call detection, which can be exploited by an attacker to cause severe performance degradation or make the service unavailable. The pattern contains multiple nested quantifiers, optional groups, and inner repetitions which make it vulnerable to catastrophic backtracking. Version 0.9.0 contains a patch for the issue.
What to do
- Upgrade vLLM to
0.9.0or later. - Do not expose the component's API or UI to the internet without authentication in front of it.
Sources
- NVD: CVE-2025-48887
- https://github.com/vllm-project/vllm/security/advisories/GHSA-w6q7-j642-7c25
- https://github.com/vllm-project/vllm/commit/4fc1bf813ad80172c1db31264beaef7d93fe0601
- https://github.com/vllm-project/vllm/pull/18454
Read more
Other vLLM CVEs
vLLM before 0.29.0 passes uploaded audio to the PyAV/FFmpeg av.open() fallback with only a file-size check, exposing FFmpeg's IAMF parser he...
A security flaw has been discovered in vllm-project vLLM up to 0.31.0. This impacts the function get_token_bin_counts_and_mask of the file v...
A security vulnerability has been detected in vllm-project vLLM up to 0.31.0. This impacts the function conv_ssm_forward of the file vllm/mo...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank...
vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through "POST /v1/r...
vLLM is an inference and serving engine for large language models. Prior to 0.28.0, the default mirrored multimodal LRU cache can commit a m...