{"id":"CVE-2025-48943","aliases":["EUVD-2025-16515","GHSA-9hcf-v7m4-6m2j","PYSEC-2025-55"],"status":"published","title":"vLLM allows clients to crash the openai server with invalid regex","description":"vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.","severity":{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-11","score":0.00508,"percentile":0.43845,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-248"],"published":"2025-05-28T19:42:12Z","modified":"2026-11-11T10:31:05Z","fixes":[{"ecosystem":"PyPI","package":"vllm","fixed_in":["0.9.0"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.8.0"},{"fixed":"0.9.0"}]}]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.8.0"},{"fixed":"0.9.0"}]}],"versions":["0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1"]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"GIT","events":[{"introduced":"0"},{"fixed":"08bf7840780980c7568c573c70a6a8db94fd45ff"}]},{"type":"ECOSYSTEM","events":[{"introduced":"0.8.0"},{"fixed":"0.9.0"}]}],"versions":["0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1"]}],"products":[{"vendor":"vllm","product":"vllm"},{"vendor":"vllm-project","product":"vllm"}],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-9hcf-v7m4-6m2j","tags":["x_refsource_CONFIRM","Vendor Advisory","advisory","web"]},{"url":"https://github.com/vllm-project/vllm/issues/17313","tags":["x_refsource_MISC","Issue Tracking","report","web"]},{"url":"https://github.com/vllm-project/vllm/pull/17623","tags":["x_refsource_MISC","Issue Tracking","Patch","fix","web","report"]},{"url":"https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff","tags":["x_refsource_MISC","Patch","fix","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2025-48943","tags":["advisory"]},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2025-55.yaml","tags":["web"]},{"url":"https://github.com/advisories/GHSA-9hcf-v7m4-6m2j"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/48xxx/CVE-2025-48943.json","tags":["advisory"]},{"url":"https://github.com/vllm-project/vllm","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2025-48943","title":"vLLM allows clients to crash the openai server with invalid regex","description":"vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.","status":"published","published":"2025-05-30T18:36:01.519Z","modified":"2025-05-30T18:56:18.715Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"cna"}],"cwes":["CWE-248"],"updated_at":"2026-11-02T14:32:41.089134Z"}],"euvd":[{"id":"EUVD-2025-16515","description":"vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.","status":"published","published":"2025-05-30T18:36:01Z","modified":"2025-05-30T18:56:18Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T20:32:33.750801Z"}],"ghsa":[{"id":"GHSA-9hcf-v7m4-6m2j","title":"vLLM allows clients to crash the openai server with invalid regex","description":"### Impact\n\nA denial of service bug caused the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to [GHSA-6qc9-v4r8-22xg](https://github.com/vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xg), but for regex instead of a JSON schema.\n\nIssue with more details: https://github.com/vllm-project/vllm/issues/17313\n\n### Patches\n\n* https://github.com/vllm-project/vllm/pull/17623","status":"published","published":"2025-05-28T19:42:12Z","modified":"2025-06-27T21:07:05Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-248"],"updated_at":"2026-11-02T14:38:48.783737Z"}],"nvd":[{"id":"CVE-2025-48943","description":"vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.","status":"published","published":"2025-05-30T19:15:30.28Z","modified":"2026-06-17T09:30:31.6Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium","assessor":"secondary"}],"cwes":["CWE-248"],"updated_at":"2026-11-02T14:11:10.143444Z"}],"osv":[{"id":"CVE-2025-48943","title":"vLLM allows clients to crash the openai server with invalid regex","description":"vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.","status":"published","published":"2025-05-30T18:36:01.519Z","modified":"2026-11-11T10:31:05.247903326Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-248"],"updated_at":"2026-11-11T11:06:34.532568Z"},{"id":"GHSA-9hcf-v7m4-6m2j","title":"vLLM allows clients to crash the openai server with invalid regex","description":"### Impact\n\nA denial of service bug caused the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to [GHSA-6qc9-v4r8-22xg](https://github.com/vllm-project/vllm/security/advisories/GHSA-6qc9-v4r8-22xg), but for regex instead of a JSON schema.\n\nIssue with more details: https://github.com/vllm-project/vllm/issues/17313\n\n### Patches\n\n* https://github.com/vllm-project/vllm/pull/17623","status":"published","published":"2025-05-28T19:42:12Z","modified":"2026-08-07T08:12:07.476205432Z","cvss":[{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-248"],"updated_at":"2026-11-02T15:46:43.875515Z"},{"id":"PYSEC-2025-55","description":"vLLM is an inference and serving engine for large language models (LLMs). Version 0.8.0 up to but excluding 0.9.0 have a Denial of Service (ReDoS) that causes the vLLM server to crash if an invalid regex was provided while using structured output. This vulnerability is similar to GHSA-6qc9-v4r8-22xg/CVE-2025-48942, but for regex instead of a JSON schema. Version 0.9.0 fixes the issue.","status":"published","published":"2025-05-30T19:15:30Z","modified":"2025-06-26T21:44:31.927402Z","updated_at":"2026-11-02T15:52:54.242332Z"}]}}