{"answers":{"affected":"It affects 1 product.","exploited":"There is no known exploitation of CVE-2025-23318 in the wild and no public exploit code.","fix":"Apply the vendor's patch.","what":"CVE-2025-23318 is a high-severity memory corruption vulnerability in Nvidia Triton Inference Server, published on 6 Aug 2025. An attacker can exploit it over the internet without logging in, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2025-23318 and fix it if it is affected.\n\nWhat it is: CVE-2025-23318 is a high-severity memory corruption vulnerability in Nvidia Triton Inference Server, published on 6 Aug 2025. An attacker can exploit it over the internet without logging in, with no action from the victim.\nExploitation: There is no known exploitation of CVE-2025-23318 in the wild and no public exploit code.\n\nAffected product: Nvidia Triton Inference Server. 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-2025-23318/ (Markdown: https://insights.sbomify.com/CVE-2025-23318/index.md)","id":"CVE-2025-23318","markdown":"https://insights.sbomify.com/CVE-2025-23318/index.md","name":"CVE-2025-23318","record":{"aliases":["GHSA-736h-fxpw-gmwm","MINI-4gc2-gprp-x96j"],"analysis":{"component_type":"server_software","fix_type":"patch","impacts":["code_execution","denial_of_service","data_modify","data_read"],"network_reachable":"yes","non_default_config":false,"product_category":"NVIDIA Triton Inference Server","requires_auth":"none","summary":"An out-of-bounds write in the Python backend allows attackers to execute code, cause denial of service, tamper with data, or disclose information.","user_interaction":"not_required","vuln_class":"memory_corruption"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"nvidia","cpe":[{"product":"triton_inference_server","vendor":"nvidia"}],"cvss":{"score":8.1,"severity":"high","source":"cna","vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-787","name":"Out-of-bounds Write"},{"id":"CWE-805","name":"Buffer Access with Incorrect Length Value"}],"description":"NVIDIA Triton Inference Server for Windows and Linux contains a vulnerability in the Python backend, where an attacker could cause an out-of-bounds write. A successful exploit of this vulnerability might lead to code execution, denial of service, data tampering, and information disclosure.","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":"Memory corruption in Triton Inference Server","id":"CVE-2025-23318","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":null,"product":"nvidia:triton_inference_server","products":["nvidia:triton_inference_server"],"type":"memory_corruption","year":"2025"},"n_packages":0,"n_references":3,"next":{"headline":"Memory corruption in Triton Inference Server","id":"CVE-2025-23319"},"packages":[],"prev":{"headline":"Code injection in Triton Inference Server","id":"CVE-2025-23317"},"products":["Triton Inference Server"],"published":"2025-08-06","related":[{"cvss_score":9.8,"headline":"Path traversal in Triton Inference Server","id":"CVE-2026-47627","kev_date_added":null,"published":"2026-08-18"},{"cvss_score":9.8,"headline":"Auth bypass in Triton Inference Server","id":"CVE-2026-24207","kev_date_added":null,"published":"2026-05-20"},{"cvss_score":9.8,"headline":"Command injection in Triton Inference Server","id":"CVE-2025-23316","kev_date_added":null,"published":"2025-09-17"},{"cvss_score":9.8,"headline":"Memory corruption in Triton Inference Server","id":"CVE-2025-23310","kev_date_added":null,"published":"2025-08-06"},{"cvss_score":9.8,"headline":"Memory corruption in Triton Inference Server","id":"CVE-2025-23311","kev_date_added":null,"published":"2025-08-06"},{"cvss_score":9.1,"headline":"Code injection in Triton Inference Server","id":"CVE-2025-23317","kev_date_added":null,"published":"2025-08-06"},{"cvss_score":9,"headline":"CVE","id":"CVE-2024-0087","kev_date_added":null,"published":"2024-05-09"}],"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":"total"},"state":"PUBLISHED","updated":"2025-08-06","vendors":["NVIDIA"]},"summary":"An out-of-bounds write in the Python backend allows attackers to execute code, cause denial of service, tamper with data, or disclose information.","url":"https://insights.sbomify.com/CVE-2025-23318/"}