{"id":"CVE-2025-48956","aliases":["EUVD-2025-25446","GHSA-rxc4-3w6r-4v47","PYSEC-2026-2021"],"status":"published","title":"vLLM API endpoints vulnerable to Denial of Service Attacks","description":"vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.","severity":{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-10","score":0.00565,"percentile":0.47245,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-400"],"published":"2025-08-21T14:24:16Z","modified":"2026-10-28T02:30:50Z","fixes":[{"ecosystem":"PyPI","package":"vllm","fixed_in":["0.10.1.1"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.1.0"},{"fixed":"0.10.1.1"}]}]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.1.0"},{"fixed":"0.10.1.1"}]}],"versions":["0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"]},{"source":"osv","ecosystem":"PyPI","package":"vllm","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0.1.0"},{"fixed":"0.10.1.1"}]}],"versions":["0.1.0","0.1.1","0.1.2","0.1.3","0.1.4","0.1.5","0.1.6","0.1.7","0.10.0","0.10.1","0.2.0","0.2.1","0.2.1.post1","0.2.2","0.2.3","0.2.4","0.2.5","0.2.6","0.2.7","0.3.0","0.3.1","0.3.2","0.3.3","0.4.0","0.4.0.post1","0.4.1","0.4.2","0.4.3","0.5.0","0.5.0.post1","0.5.1","0.5.2","0.5.3","0.5.3.post1","0.5.4","0.5.5","0.6.0","0.6.1","0.6.1.post1","0.6.1.post2","0.6.2","0.6.3","0.6.3.post1","0.6.4","0.6.4.post1","0.6.5","0.6.6","0.6.6.post1","0.7.0","0.7.1","0.7.2","0.7.3","0.8.0","0.8.1","0.8.2","0.8.3","0.8.4","0.8.5","0.8.5.post1","0.9.0","0.9.0.1","0.9.1","0.9.2"]}],"products":[{"vendor":"vllm","product":"vllm"},{"vendor":"vllm-project","product":"vllm"}],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-rxc4-3w6r-4v47","tags":["x_refsource_CONFIRM","Vendor Advisory","advisory","web"]},{"url":"https://github.com/vllm-project/vllm/pull/23267","tags":["x_refsource_MISC","Issue Tracking","Patch","fix","web"]},{"url":"https://github.com/vllm-project/vllm/commit/d8b736f913a59117803d6701521d2e4861701944","tags":["x_refsource_MISC","Patch","fix","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2025-48956","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-rxc4-3w6r-4v47","tags":["advisory"]},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/vllm/PYSEC-2026-2021.yaml","tags":["web"]},{"url":"https://github.com/vllm-project/vllm","tags":["package"]},{"url":"https://pypi.org/project/vllm","tags":["web","package"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/48xxx/CVE-2025-48956.json","tags":["advisory"]}],"sources":{"cve":[{"id":"CVE-2025-48956","title":"vLLM API endpoints vulnerable to Denial of Service Attacks","description":"vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.","status":"published","published":"2025-08-21T14:41:03.889Z","modified":"2025-08-21T15:02:09.023Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high","assessor":"cna"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T14:32:41.089134Z"}],"euvd":[{"id":"EUVD-2025-25446","description":"vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.","status":"published","published":"2025-08-21T14:41:03Z","modified":"2025-08-21T15:02:09Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high"}],"updated_at":"2026-11-02T20:31:55.037702Z"}],"ghsa":[{"id":"GHSA-rxc4-3w6r-4v47","title":"vllm API endpoints vulnerable to Denial of Service Attacks","description":"### Summary\nA Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user.\n\n### Details\nThe vulnerability leverages the abuse of HTTP headers. By setting a header such as `X-Forwarded-For` to a very large value like `(\"A\" * 5_800_000_000)`, the server's HTTP parser or application logic may attempt to load the entire request into memory, overwhelming system resources.\n\n### Impact\n_What kind of vulnerability is it? Who is impacted?_\nType of vulnerability: Denial of Service (DoS)\n\n### Resolution\nUpgrade to a version of vLLM that includes appropriate HTTP limits by deafult, or use a proxy in front of vLLM which provides protection against this issue.","status":"published","published":"2025-08-21T14:24:16Z","modified":"2026-07-17T16:14:42Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T14:40:44.915484Z"}],"nvd":[{"id":"CVE-2025-48956","description":"vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.","status":"published","published":"2025-08-21T15:15:32.23Z","modified":"2026-06-17T09:30:33.773Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high","assessor":"secondary"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T14:11:25.261243Z"}],"osv":[{"id":"CVE-2025-48956","title":"vLLM API endpoints vulnerable to Denial of Service Attacks","description":"vLLM is an inference and serving engine for large language models (LLMs). From 0.1.0 to before 0.10.1.1, a Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user. This vulnerability is fixed in 0.10.1.1.","status":"published","published":"2025-08-21T14:41:03.889Z","modified":"2026-10-28T02:30:50.719971607Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T15:44:50.037003Z"},{"id":"GHSA-rxc4-3w6r-4v47","title":"vllm API endpoints vulnerable to Denial of Service Attacks","description":"### Summary\nA Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user.\n\n### Details\nThe vulnerability leverages the abuse of HTTP headers. By setting a header such as `X-Forwarded-For` to a very large value like `(\"A\" * 5_800_000_000)`, the server's HTTP parser or application logic may attempt to load the entire request into memory, overwhelming system resources.\n\n### Impact\n_What kind of vulnerability is it? Who is impacted?_\nType of vulnerability: Denial of Service (DoS)\n\n### Resolution\nUpgrade to a version of vLLM that includes appropriate HTTP limits by deafult, or use a proxy in front of vLLM which provides protection against this issue.","status":"published","published":"2025-08-21T14:24:16Z","modified":"2026-09-10T03:50:27.365803772Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high"}],"cwes":["CWE-400"],"updated_at":"2026-11-02T15:46:56.639206Z"},{"id":"PYSEC-2026-2021","title":"vllm API endpoints vulnerable to Denial of Service Attacks","description":"### Summary\nA Denial of Service (DoS) vulnerability can be triggered by sending a single HTTP GET request with an extremely large header to an HTTP endpoint. This results in server memory exhaustion, potentially leading to a crash or unresponsiveness. The attack does not require authentication, making it exploitable by any remote user.\n\n### Details\nThe vulnerability leverages the abuse of HTTP headers. By setting a header such as `X-Forwarded-For` to a very large value like `(\"A\" * 5_800_000_000)`, the server's HTTP parser or application logic may attempt to load the entire request into memory, overwhelming system resources.\n\n### Impact\n_What kind of vulnerability is it? Who is impacted?_\nType of vulnerability: Denial of Service (DoS)\n\n### Resolution\nUpgrade to a version of vLLM that includes appropriate HTTP limits by deafult, or use a proxy in front of vLLM which provides protection against this issue.","status":"published","published":"2026-07-07T16:03:01.55974Z","modified":"2026-07-07T17:48:17.626607221Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high"}],"updated_at":"2026-11-02T15:52:55.537808Z"}]}}