{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-57173","assignerOrgId":"a0819718-46f1-4df5-94e2-005712e83aaa","state":"PUBLISHED","assignerShortName":"GitHub_M","dateReserved":"2026-06-24T01:47:55.285Z","datePublished":"2026-09-16T16:34:39.144Z","dateUpdated":"2026-09-16T16:34:39.144Z"},"containers":{"cna":{"title":"vLLM: Unauthenticated audio decompression-bomb DoS in /v1/chat/completions","problemTypes":[{"descriptions":[{"cweId":"CWE-770","lang":"en","description":"CWE-770: Allocation of Resources Without Limits or Throttling","type":"CWE"}]}],"metrics":[{"cvssV3_1":{"attackComplexity":"LOW","attackVector":"NETWORK","availabilityImpact":"HIGH","baseScore":6.5,"baseSeverity":"MEDIUM","confidentialityImpact":"NONE","integrityImpact":"NONE","privilegesRequired":"LOW","scope":"UNCHANGED","userInteraction":"NONE","vectorString":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","version":"3.1"}}],"references":[{"name":"https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr","tags":["x_refsource_CONFIRM"],"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-hcwq-8wjf-3gcr"},{"name":"https://github.com/vllm-project/vllm/pull/45908","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/pull/45908"},{"name":"https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/commit/3d20275bb4d434f53055c3c0b645fd8bb072965e"},{"name":"https://github.com/vllm-project/vllm/releases/tag/v0.24.0","tags":["x_refsource_MISC"],"url":"https://github.com/vllm-project/vllm/releases/tag/v0.24.0"}],"affected":[{"vendor":"vllm-project","product":"vllm","versions":[{"version":"< 0.24.0","status":"affected"}]}],"providerMetadata":{"orgId":"a0819718-46f1-4df5-94e2-005712e83aaa","shortName":"GitHub_M","dateUpdated":"2026-09-16T16:34:39.144Z"},"descriptions":[{"lang":"en","value":"vLLM is an inference and serving engine for large language models. Prior to 0.24.0, the input_audio handling path for /v1/chat/completions calls AudioMediaIO.load_bytes or AudioMediaIO.load_file without passing VLLM_MAX_AUDIO_DECODE_DURATION_S to the shared audio decoder. An unauthenticated client can therefore submit a small compressed audio input that expands into a very large float32 PCM allocation, bypassing the duration guard already used by /v1/audio/transcriptions and causing an out-of-memory worker crash. Inline data URLs reach this path without being bounded by VLLM_AUDIO_FETCH_TIMEOUT. The issue affects deployments serving an audio-capable model, and authentication changes only the deployment-specific reachability. This issue is fixed in version 0.24.0."}],"source":{"advisory":"GHSA-hcwq-8wjf-3gcr","discovery":"UNKNOWN"}}}}