{"answers":{"affected":"3 open source packages ship an affected version, including vllm. It affects 1 product.","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-73558 exists.","fix":"Upgrade vllm to 0.27.0 or later.","what":"CVE-2026-73558 is a medium-severity vulnerability in Vllm Vllm, published on 13 Aug 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link."},"fix_prompt":"Check this codebase for CVE-2026-73558 and fix it if it is affected.\n\nWhat it is: CVE-2026-73558 is a medium-severity vulnerability in Vllm Vllm, published on 13 Aug 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.\nExploitation: It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-73558 exists.\n\nAffected packages and fixed versions:\n- vllm (PyPI): affected all versions; fixed in 0.27.0\n- vllm (PyPI): affected all versions; fixed in 0.27.0\n- vllm (PyPI): affected all versions; fixed in 0.27.0\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-2026-73558/ (Markdown: https://insights.sbomify.com/CVE-2026-73558/index.md)","id":"CVE-2026-73558","markdown":"https://insights.sbomify.com/CVE-2026-73558/index.md","name":"CVE-2026-73558","record":{"aliases":["GHSA-7m6h-x95x-82q5","MINI-5654-wgg2-f6c6","MINI-7hhv-gr99-276x","MINI-qmmq-rx4c-rjgq","PYSEC-2026-3935"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["data_read"],"network_reachable":"yes","non_default_config":false,"product_category":"LLM inference engine","requires_auth":"none","summary":"An integer overflow in vLLM allows attackers to read other users' inference results via batched requests.","user_interaction":"required","vuln_class":"integer_overflow"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"vllm","vendor":"vllm"}],"cvss":{"score":5.3,"severity":"medium","source":"cna","vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:N/A:N","version":"3.1"},"cwes":[{"id":"CWE-190","name":"Integer Overflow or Wraparound"}],"description":"vLLM is an inference and serving engine for large language models. Prior to 0.27.0, an integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input, allowing a request processed in the same inference batch to receive a partial or complete copy of another user's inference result. This issue is fixed in version 0.27.0.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":true,"headline":"vLLM: Cross-User Data Leak Vulnerability","id":"CVE-2026-73558","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":"vllm:vllm","products":["vllm:vllm"],"type":"integer_overflow","year":"2026"},"n_packages":3,"n_references":5,"next":{"headline":"vLLM: Completion prompt lists fan out into unbounded engine requests","id":"CVE-2026-73559"},"packages":[{"ecosystem":"PyPI","fixed":["0.27.0"],"introduced":["0"],"last_affected":[],"package":"vllm","purl":null,"source":"GHSA-7m6h-x95x-82q5"},{"ecosystem":"PyPI","fixed":["0.27.0"],"introduced":["0"],"last_affected":[],"package":"vllm","purl":"pkg:pypi/vllm","source":"GHSA-7m6h-x95x-82q5"},{"ecosystem":"PyPI","fixed":["0.27.0"],"introduced":["0"],"last_affected":[],"package":"vllm","purl":"pkg:pypi/vllm","source":"PYSEC-2026-3935"}],"prev":{"headline":"vLLM: Incomplete CVE-2025-62164 remediation can be bypassed by concurrent prompt parts","id":"CVE-2026-73557"},"products":["vllm"],"published":"2026-08-13","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":"CC BY 4.0","name":"GitHub Advisory Database","prefix":"GHSA"},{"class":"attribution","licence":"CC BY 4.0","name":"PyPA Advisory Database","prefix":"PYSEC"},{"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":"poc","technical_impact":"partial"},"state":"PUBLISHED","updated":"2026-08-13","vendors":["vllm-project"]},"summary":"An integer overflow in vLLM allows attackers to read other users' inference results via batched requests.","url":"https://insights.sbomify.com/CVE-2026-73558/"}