{"action":"Upgrade vllm to 0.9.0 or later.","affected":[{"fixed":"0.9.0","introduced":"0.8.0"}],"component":"vllm","cve_ids":["CVE-2025-48943"],"ecosystem":"PyPI","epss":0.00487,"exploited":false,"fixed_versions":["0.9.0"],"ghsa_id":"GHSA-9hcf-v7m4-6m2j","id":"tcs_01M5KGPR968JN0XS7F7V64X3S2","modified_at":"2025-06-26T21:44:31.927402Z","published_at":"2025-05-30T19:15:30Z","references":["https://osv.dev/vulnerability/PYSEC-2025-55","https://github.com/vllm-project/vllm/security/advisories/GHSA-9hcf-v7m4-6m2j","https://github.com/vllm-project/vllm/commit/08bf7840780980c7568c573c70a6a8db94fd45ff","https://github.com/vllm-project/vllm/pull/17623","https://github.com/vllm-project/vllm/issues/17313"],"severity":{"label":"unknown"},"sources":[{"source":"osv","source_id":"PYSEC-2025-55","url":"https://osv.dev/vulnerability/PYSEC-2025-55"}],"summary":"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 re"}