Vulnerabilities · 2025 · Vllm
CVE-2025-48887
Vllm vulnerability
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.
Affected products
Vllm. The exact versions are in the references.
What to do now
- Check your exposureFind out whether Vllm runs anywhere in your environment, including systems of suppliers.
- UpdateInstall the version in which the vendor fixed the vulnerability. The references lead to the advisory.
- Set the orderSystems that can be reached from the internet come first, then the rest.
References
- github.com/vllm-project/vllm/security/advisories/GHSA-w6q7-j642-7c25 · Exploit
- github.com/vllm-project/vllm/commit/4fc1bf813ad80172c1db31264beaef7d93fe0601 · Patch
- github.com/vllm-project/vllm/pull/18454 · Patch
- nvd.nist.gov/vuln/detail/CVE-2025-48887
- github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-50.yaml
- github.com/advisories/GHSA-w6q7-j642-7c25
- nvd.nist.gov/vuln/detail/CVE-2025-48887
- cve.org/CVERecord?id=CVE-2025-48887
More vulnerabilities in Vllm products
Data: CVE list and the NVD. This product uses data from the NVD API but is not endorsed or certified by the NVD.