{"answers":{"affected":"3 open source packages ship an affected version, including vllm. It affects 1 product.","exploited":"There is no known exploitation of CVE-2026-105755 in the wild and no public exploit code.","fix":"Upgrade vllm to 0.30.0 or later.","what":"CVE-2026-105755 is a medium-severity vulnerability in Vllm Vllm, published on 5 Oct 2026. Any signed-in user can exploit it over the network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-105755 and fix it if it is affected.\n\nWhat it is: CVE-2026-105755 is a medium-severity vulnerability in Vllm Vllm, published on 5 Oct 2026. Any signed-in user can exploit it over the network, with no action from the victim.\nExploitation: There is no known exploitation of CVE-2026-105755 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- vllm (PyPI): affected all versions; fixed in 0.30.0\n- vllm (PyPI): affected all versions; fixed in 0.30.0\n- vllm (PyPI): affected all versions; fixed in 0.30.0\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-2026-105755/ (Markdown: https://insights.sbomify.com/CVE-2026-105755/index.md)","id":"CVE-2026-105755","markdown":"https://insights.sbomify.com/CVE-2026-105755/index.md","name":"CVE-2026-105755","record":{"aliases":["GHSA-2phq-3phc-84px","MINI-64jj-xhc3-h95r","MINI-v352-vqhr-2q3m","MINI-wx4h-g8q2-f3pm","PYSEC-2026-4198"],"analysis":{"component_type":"server_software","fix_type":"upgrade","impacts":["data_read","denial_of_service"],"network_reachable":"yes","non_default_config":false,"product_category":"LLM inference server","requires_auth":"low_privilege","summary":"Attackers can manipulate cached query embeddings via shared request IDs, causing incorrect scoring results or service errors in vLLM.","user_interaction":"not_required","vuln_class":"race_condition"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"vllm","vendor":"vllm"}],"cvss":{"score":4.2,"severity":"medium","source":"cna","vector":"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:L","version":"3.1"},"cwes":[{"id":"CWE-639","name":"Authorization Bypass Through User-Controlled Key"}],"description":"vLLM is an inference and serving engine for large language models. Prior to 0.30.0, flash late-interaction scoring at the /score and /rerank endpoints derives each worker's query_key value from the caller-controlled X-Request-Id header. A concurrent request that reuses a victim's identifier can overwrite the cached query embedding so the victim's documents are scored against the attacker's query, and shared use counters can also cause a late-interaction cache-miss error. This issue is fixed in version 0.30.0.","ecosystems":["PyPI"],"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: Flash late-interaction scoring caches query embeddings under a caller-controlled request id — cross-request integrity break and induced errors on `/score` and `/rerank`","id":"CVE-2026-105755","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":"vllm:vllm","products":["vllm:vllm"],"type":"race_condition","year":"2026"},"n_packages":3,"n_references":4,"next":{"headline":"vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service","id":"CVE-2026-105756"},"packages":[{"ecosystem":"PyPI","fixed":["0.30.0"],"introduced":["0"],"last_affected":[],"package":"vllm","purl":null,"source":"GHSA-2phq-3phc-84px"},{"ecosystem":"PyPI","fixed":["0.30.0"],"introduced":["0"],"last_affected":[],"package":"vllm","purl":"pkg:pypi/vllm","source":"GHSA-2phq-3phc-84px"},{"ecosystem":"PyPI","fixed":["0.30.0"],"introduced":["0"],"last_affected":[],"package":"vllm","purl":"pkg:pypi/vllm","source":"PYSEC-2026-4198"}],"prev":{"headline":"vLLM: Scale-out disaggregated multimodal transport trusts caller-supplied features","id":"CVE-2026-105754"},"products":["vllm"],"published":"2026-10-05","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":"none","technical_impact":"partial"},"state":"PUBLISHED","updated":"2026-10-06","vendors":["vllm-project"]},"summary":"Attackers can manipulate cached query embeddings via shared request IDs, causing incorrect scoring results or service errors in vLLM.","url":"https://insights.sbomify.com/CVE-2026-105755/"}