{"answers":{"affected":"It affects 1 product.","exploited":"There is no known exploitation of CVE-2026-90554 in the wild and no public exploit code.","fix":"Upgrade to a fixed version.","what":"CVE-2026-90554 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 12 Sep 2026. It can only be exploited from the same machine or local network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-90554 and fix it if it is affected.\n\nWhat it is: CVE-2026-90554 is a medium-severity denial of service vulnerability in Vllm Vllm, published on 12 Sep 2026. It can only be exploited from the same machine or local network, with no action from the victim.\nExploitation: There is no known exploitation of CVE-2026-90554 in the wild and no public exploit code.\n\nAffected product: Vllm Vllm. No package-level version data is available, so check the vendor advisory linked from the reference page.\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-90554/ (Markdown: https://insights.sbomify.com/CVE-2026-90554/index.md)","id":"CVE-2026-90554","markdown":"https://insights.sbomify.com/CVE-2026-90554/index.md","name":"CVE-2026-90554","record":{"aliases":["GHSA-936p-m5pv-vvjf","GHSA-m39m-2pqx-3vm2","MINI-96jv-wj5w-r4mr","MINI-pgrg-j7m3-7mrr","MINI-vmwx-cvrr-v6cv"],"analysis":{"component_type":"server_software","fix_type":"upgrade","impacts":["denial_of_service"],"network_reachable":"adjacent_or_local","non_default_config":true,"product_category":"LLM serving library","requires_auth":"none","summary":"Attackers can cause denial of service by sending compressed video inputs to vLLM servers configured for audio extraction, forcing excessive memory allocation.","user_interaction":"not_required","vuln_class":"denial_of_service"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"VulnCheck","cpe":[{"product":"vllm","vendor":"vllm"}],"cvss":{"score":6.9,"severity":"medium","source":"cna","vector":"CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","version":"4.0"},"cwes":[{"id":"CWE-400","name":"Uncontrolled Resource Consumption"}],"description":"vLLM versions \u003e=0.10.2 and \u003c0.28.0 do not apply any audio decode-size or duration limit when extracting audio from video input for NanoNemotronVL models. In nano_nemotron_vl.py, _extract_audio_from_videos calls load_audio_pyav(BytesIO(video_bytes)) without the max_duration_s or max_decode_bytes parameters, so neither VLLM_MAX_AUDIO_DECODE_DURATION_S nor VLLM_MAX_AUDIO_DECODE_BYTES is enforced (unlike the direct audio upload path in AudioMediaIO). When a NanoNemotronVL model is served with use_audio_in_video=True, an attacker who supplies a small, highly compressed video as multimodal input can force the server to allocate gigabytes of memory during audio decoding, resulting in a denial of service. Fixed in vLLM 0.28.0.","ecosystems":[],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"none_known"},"has_fix":true,"headline":"vLLM before 0.28.0 Denial of Service via audio extraction","id":"CVE-2026-90554","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":null,"product":"vllm:vllm","products":["vllm:vllm"],"type":"denial_of_service","year":"2026"},"n_packages":0,"n_references":2,"next":{"headline":"vLLM before 0.28.0 Denial of Service via Audio Header","id":"CVE-2026-90555"},"packages":[],"prev":{"headline":"vLLM before 0.28.0 Remote Code Execution via LlavaOnevision2 processor","id":"CVE-2026-90553"},"products":["vLLM"],"published":"2026-09-12","related":[{"cvss_score":10,"headline":"vLLM Vulnerable to Remote Code Execution via Mooncake Integration","id":"CVE-2025-32444","kev_date_added":null,"published":"2025-04-30"},{"cvss_score":9.8,"headline":"vLLM leaks a heap address when PIL throws an error","id":"CVE-2026-22778","kev_date_added":null,"published":"2026-02-02"},{"cvss_score":9.8,"headline":"vLLM Allows Remote Code Execution via PyNcclPipe Communication Service","id":"CVE-2025-47277","kev_date_added":null,"published":"2025-05-20"},{"cvss_score":9.8,"headline":"Remote Code Execution in vllm-project/vllm","id":"CVE-2024-11041","kev_date_added":null,"published":"2025-03-20"},{"cvss_score":9.1,"headline":"vLLM: OpenAI auth bypass","id":"CVE-2026-48746","kev_date_added":null,"published":"2026-06-22"},{"cvss_score":9.1,"headline":"vLLM Allows Remote Code Execution via Mooncake Integration","id":"CVE-2025-29783","kev_date_added":null,"published":"2025-03-19"},{"cvss_score":8.8,"headline":"vLLM 0.9.2 before 0.24.0 SSRF via X-Request-Id in P2pNcclConnector","id":"CVE-2026-116176","kev_date_added":null,"published":"2026-10-25"}],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"US public information, NVD API terms","name":"NVD"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"no","exploitation":"none","technical_impact":"partial"},"state":"PUBLISHED","updated":"2026-09-14","vendors":["vllm-project"]},"summary":"Attackers can cause denial of service by sending compressed video inputs to vLLM servers configured for audio extraction, forcing excessive memory allocation.","url":"https://insights.sbomify.com/CVE-2026-90554/"}