{"dataType":"CVE_RECORD","dataVersion":"5.2","cveMetadata":{"cveId":"CVE-2026-100651","assignerOrgId":"83251b91-4cc7-4094-a5c7-464a1b83ea10","state":"PUBLISHED","assignerShortName":"VulnCheck","dateReserved":"2026-09-26T02:33:07.899Z","datePublished":"2026-09-26T13:23:21.141Z","dateUpdated":"2026-09-26T13:23:21.141Z"},"containers":{"cna":{"providerMetadata":{"orgId":"83251b91-4cc7-4094-a5c7-464a1b83ea10","shortName":"VulnCheck","dateUpdated":"2026-09-26T13:23:21.141Z"},"datePublic":"2026-09-12T00:00:00.000Z","title":"vllm before 0.29.0 Denial of Service via Decoder Prompt Length Bypass","descriptions":[{"lang":"en","value":"vLLM before 0.29.0 fails to enforce decoder prompt-length validation on the disaggregated serving endpoint /inference/v1/generate. When the request contains a 'features' (multimodal) payload, vllm/entrypoints/serve/disagg/serving.py builds a multimodal EngineInput directly from the caller-supplied token_ids, and GenerateRequest.token_ids (vllm/entrypoints/serve/disagg/protocol.py) is not checked against model_config.max_model_len. For multimodal processors that report skip_prompt_length_check=True (for example Nemotron Parse, Whisper, and FireRedLID), InputProcessor._validate_prompt_len() returns immediately for both encoder and decoder prompts, so an overlong prompt becomes an EngineCoreRequest and reaches the worker input-batch copy into a fixed max_model_len-wide NumPy row. A client able to reach the endpoint on an affected model configuration can therefore submit an overlong token_ids list to trigger a worker failure and denial of service. Fixed in 0.29.0."}],"problemTypes":[{"descriptions":[{"lang":"en","description":"Uncontrolled Resource Consumption","cweId":"CWE-400","type":"CWE"}]}],"affected":[{"vendor":"vllm-project","product":"vllm","defaultStatus":"unaffected","packageURL":"pkg:pypi/vllm","versions":[{"version":"0","status":"affected","versionType":"semver","lessThan":"0.29.0"},{"version":"0.29.0","status":"unaffected","versionType":"semver"}]}],"cpeApplicability":[{"nodes":[{"operator":"OR","negate":false,"cpeMatch":[{"vulnerable":true,"criteria":"cpe:2.3:a:vllm:vllm:*:*:*:*:*:*:*:*","versionEndExcluding":"0.29.0"}]}]}],"metrics":[{"format":"CVSS","cvssV4_0":{"version":"4.0","vectorString":"CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","attackVector":"NETWORK","attackComplexity":"LOW","attackRequirements":"NONE","privilegesRequired":"LOW","userInteraction":"NONE","vulnConfidentialityImpact":"NONE","vulnIntegrityImpact":"NONE","vulnAvailabilityImpact":"HIGH","subConfidentialityImpact":"NONE","subIntegrityImpact":"NONE","subAvailabilityImpact":"NONE","baseScore":7.1,"baseSeverity":"HIGH"}},{"format":"CVSS","cvssV3_1":{"version":"3.1","vectorString":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","attackVector":"NETWORK","attackComplexity":"LOW","privilegesRequired":"LOW","userInteraction":"NONE","scope":"UNCHANGED","confidentialityImpact":"NONE","integrityImpact":"NONE","availabilityImpact":"HIGH","baseScore":6.5,"baseSeverity":"MEDIUM"}}],"references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-3mqx-f33v-vgp9","tags":["vendor-advisory"],"name":"GitHub Security Advisory (GHSA-3mqx-f33v-vgp9)"},{"name":"VulnCheck Advisory: vllm before 0.29.0 Denial of Service via Decoder Prompt Length Bypass","tags":["third-party-advisory"],"url":"https://www.vulncheck.com/advisories/vllm-before-0.29.0-denial-of-service-via-decoder-prompt-length-bypass"}],"credits":[{"lang":"en","value":"rexpository","type":"reporter"},{"lang":"en","value":"jperezdealgaba","type":"coordinator"}],"x_generator":{"engine":"vulncheck-endgame"}}}}