{"answers":{"affected":"","exploited":"It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-4944 exists.","fix":"No fix has been published for CVE-2026-4944 yet. Limit exposure of the affected software until one is available.","what":"CVE-2026-4944 is a high-severity code injection vulnerability in vllm-project/vllm, published on 28 May 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-2026-4944 and fix it if it is affected.\n\nWhat it is: CVE-2026-4944 is a high-severity code injection vulnerability in vllm-project/vllm, published on 28 May 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-2026-4944 exists.\n\nAffected product: vllm-project/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-2026-4944/ (Markdown: https://insights.sbomify.com/CVE-2026-4944/index.md)","id":"CVE-2026-4944","markdown":"https://insights.sbomify.com/CVE-2026-4944/index.md","name":"CVE-2026-4944","record":{"aliases":["GHSA-g57c-wgqx-8wx7"],"analysis":{"component_type":"library","fix_type":"patch","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"LLM inference library","requires_auth":"none","summary":"Hardcoded trust_remote_code setting in vLLM allows remote code execution via malicious models, bypassing user security controls.","user_interaction":"required","vuln_class":"code_injection"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"@huntr_ai","cpe":[],"cvss":{"score":8.8,"severity":"high","source":"cna","vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","version":"3.0"},"cwes":[{"id":"CWE-22","name":"Improper Limitation of a Pathname to a Restricted Directory"}],"description":"vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `vllm/model_executor/models/kimi_k25.py`). This bypasses the user's explicit `--trust-remote-code=False` setting, enabling remote code execution via malicious HuggingFace model repositories. This issue is an incomplete fix for CVE-2025-66448 and CVE-2026-22807, as it affects separate code paths in model implementation files. Deployments loading NemotronVL or KimiK25 models are particularly impacted.","ecosystems":[],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"weaponised"},"has_fix":null,"headline":"Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control","id":"CVE-2026-4944","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":null,"product":null,"products":[],"type":"code_injection","year":"2026"},"n_packages":0,"n_references":1,"next":{"headline":"Otter Blocks \u003c= 3.1.7 - Missing Authorization to Unauthenticated Purchase Verification Bypass","id":"CVE-2026-4945"},"packages":[],"prev":{"headline":"IBM i is Affected by Algorithm Downgrade in Transport Layer Security []","id":"CVE-2026-4942"},"products":["vllm-project/vllm"],"published":"2026-05-28","related":[],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"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":"total"},"state":"PUBLISHED","updated":"2026-05-28","vendors":["vllm-project"]},"summary":"Hardcoded trust_remote_code setting in vLLM allows remote code execution via malicious models, bypassing user security controls.","url":"https://insights.sbomify.com/CVE-2026-4944/"}