{"answers":{"affected":"3 open source packages ship an affected version, including vllm. It affects 1 product.","exploited":"There is no known exploitation of CVE-2026-22807 in the wild and no public exploit code.","fix":"Upgrade vllm to 0.14.0 or later.","what":"CVE-2026-22807 is a high-severity code injection vulnerability in Vllm Vllm, published on 21 Jan 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-2026-22807 and fix it if it is affected.\n\nWhat it is: CVE-2026-22807 is a high-severity code injection vulnerability in Vllm Vllm, published on 21 Jan 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: There is no known exploitation of CVE-2026-22807 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- vllm (PyPI): affected from 0.10.1; fixed in 0.14.0\n- vllm (PyPI): affected from 0.10.1; fixed in 0.14.0\n- vllm (PyPI): affected from 0.10.1; fixed in 0.14.0\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-2026-22807/ (Markdown: https://insights.sbomify.com/CVE-2026-22807/index.md)","id":"CVE-2026-22807","markdown":"https://insights.sbomify.com/CVE-2026-22807/index.md","name":"CVE-2026-22807","record":{"aliases":["GHSA-2pc9-4j83-qjmr","PYSEC-2026-2010"],"analysis":{"component_type":"server_software","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"LLM inference engine","requires_auth":"none","summary":"Attackers can execute arbitrary code on vLLM hosts by supplying malicious model repositories, bypassing trust_remote_code checks during initialization.","user_interaction":"required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"vllm","vendor":"vllm"}],"cvss":{"score":8.8,"severity":"high","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-94","name":"Improper Control of Generation of Code"}],"description":"vLLM is an inference and serving engine for large language models (LLMs). Starting in version 0.10.1 and prior to version 0.14.0, vLLM loads Hugging Face `auto_map` dynamic modules during model resolution without gating on `trust_remote_code`, allowing attacker-controlled Python code in a model repo/path to execute at server startup. An attacker who can influence the model repo/path (local directory or remote Hugging Face repo) can achieve arbitrary code execution on the vLLM host during model load. This happens before any request handling and does not require API access. Version 0.14.0 fixes the issue.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":"2026-01-31","github_poc":1,"max_poc_stars":0,"metasploit":0,"nuclei":0,"refs":[{"date":"2026-01-31T10:52:29Z","kind":"github_poc","ref":"https://github.com/otakuliu/CVE-2026-22807_Range","stars":0,"title":"CVE-2026-22807的靶场"}],"tier":"poc_unverified"},"has_fix":true,"headline":"vLLM affected by RCE via auto_map dynamic module loading during model initialization","id":"CVE-2026-22807","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":"vllm:vllm","products":["vllm:vllm"],"type":"code_injection","year":"2026"},"n_packages":3,"n_references":4,"next":{"headline":"Fleet Windows MDM endpoint has a Cross-site Scripting vulnerability","id":"CVE-2026-22808"},"packages":[{"ecosystem":"PyPI","fixed":["0.14.0"],"introduced":["0.10.1"],"last_affected":[],"package":"vllm","purl":null,"source":"GHSA-2pc9-4j83-qjmr"},{"ecosystem":"PyPI","fixed":["0.14.0"],"introduced":["0.10.1"],"last_affected":[],"package":"vllm","purl":"pkg:pypi/vllm","source":"GHSA-2pc9-4j83-qjmr"},{"ecosystem":"PyPI","fixed":["0.14.0"],"introduced":["0.10.1"],"last_affected":[],"package":"vllm","purl":"pkg:pypi/vllm","source":"PYSEC-2026-2010"}],"prev":{"headline":"vCluster Platform's Access Keys Allows Access Beyond Scope","id":"CVE-2026-22806"},"products":["vllm"],"published":"2026-01-21","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)"},{"class":"open","licence":"CC0","name":"PoC-in-GitHub"}],"ssvc":{"automatable":"no","exploitation":"none","technical_impact":"total"},"state":"PUBLISHED","updated":"2026-07-21","vendors":["vllm-project"]},"summary":"Attackers can execute arbitrary code on vLLM hosts by supplying malicious model repositories, bypassing trust_remote_code checks during initialization.","url":"https://insights.sbomify.com/CVE-2026-22807/"}