{"answers":{"affected":"It affects 1 product.","exploited":"There is no known exploitation of CVE-2025-33255 in the wild and no public exploit code.","fix":"No fix has been published for CVE-2025-33255 yet. Limit exposure of the affected software until one is available.","what":"CVE-2025-33255 is a high-severity unsafe deserialization vulnerability in NVIDIA TensorRT-LLM, published on 20 May 2026. It can only be exploited from the same machine or local network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2025-33255 and fix it if it is affected.\n\nWhat it is: CVE-2025-33255 is a high-severity unsafe deserialization vulnerability in NVIDIA TensorRT-LLM, published on 20 May 2026. It can only be exploited from the same machine or local network, with no action from the victim.\nExploitation: There is no known exploitation of CVE-2025-33255 in the wild and no public exploit code.\n\nAffected product: NVIDIA TensorRT-LLM. 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-2025-33255/ (Markdown: https://insights.sbomify.com/CVE-2025-33255/index.md)","id":"CVE-2025-33255","markdown":"https://insights.sbomify.com/CVE-2025-33255/index.md","name":"CVE-2025-33255","record":{"aliases":["GHSA-gvr5-23jj-pf9p"],"analysis":{"component_type":"library","fix_type":"patch","impacts":["code_execution","denial_of_service","data_modify","data_read"],"network_reachable":"adjacent_or_local","non_default_config":false,"product_category":"TensorRT-LLM library","requires_auth":"high_privilege","summary":"An attacker can exploit unsafe deserialization in the MPI server to execute code, cause denial of service, tamper with data, or disclose information.","user_interaction":"not_required","vuln_class":"deserialization"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"nvidia","cpe":[{"product":"tensorrt_llm","vendor":"nvidia"}],"cvss":{"score":7.5,"severity":"high","source":"cna","vector":"CVSS:3.1/AV:L/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-502","name":"Deserialization of Untrusted Data"}],"description":"NVIDIA TRT-LLM for any platform contains a vulnerability in MPI server, where an attacker could cause an unsafe deserialization. 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":null,"headline":"Deserialization in TensorRT-LLM","id":"CVE-2025-33255","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":null,"product":null,"products":[],"type":"deserialization","year":"2025"},"n_packages":0,"n_references":3,"next":{"headline":"Selea Targa IP OCR-ANPR Camera Server-Side Request Forgery","id":"CVE-2025-34021"},"packages":[],"prev":{"headline":"Race condition in Triton Inference Server","id":"CVE-2025-33254"},"products":["TensorRT-LLM"],"published":"2026-05-20","related":[{"cvss_score":7.5,"headline":"Deserialization in TensorRT-LLM","id":"CVE-2026-24163","kev_date_added":null,"published":"2026-05-20"},{"cvss_score":6.3,"headline":"Deserialization in TensorRT-LLM","id":"CVE-2026-24142","kev_date_added":null,"published":"2026-05-20"},{"cvss_score":5.5,"headline":"Null dereference in TensorRT-LLM","id":"CVE-2026-24160","kev_date_added":null,"published":"2026-05-20"}],"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":"2026-05-20","vendors":["NVIDIA"]},"summary":"An attacker can exploit unsafe deserialization in the MPI server to execute code, cause denial of service, tamper with data, or disclose information.","url":"https://insights.sbomify.com/CVE-2025-33255/"}