{"answers":{"affected":"3 open source packages ship an affected version, including vllm. It affects 1 product.","exploited":"There is no known exploitation of CVE-2025-24357 in the wild and no public exploit code.","fix":"Upgrade vllm to 0.7.0 or later.","what":"CVE-2025-24357 is a high-severity unsafe deserialization vulnerability in Vllm Vllm, published on 27 Jan 2025. 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-2025-24357 and fix it if it is affected.\n\nWhat it is: CVE-2025-24357 is a high-severity unsafe deserialization vulnerability in Vllm Vllm, published on 27 Jan 2025. 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-2025-24357 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- vllm (PyPI): affected all versions; fixed in 0.7.0\n- vllm (PyPI): affected all versions; fixed in 0.7.0\n- vllm (PyPI): affected all versions; fixed in 0.7.0\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-2025-24357/ (Markdown: https://insights.sbomify.com/CVE-2025-24357/index.md)","id":"CVE-2025-24357","markdown":"https://insights.sbomify.com/CVE-2025-24357/index.md","name":"CVE-2025-24357","record":{"aliases":["GHSA-rh4j-5rhw-hr54","PYSEC-2025-58"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["code_execution"],"network_reachable":"yes","non_default_config":false,"product_category":"LLM inference library","requires_auth":"none","summary":"Attackers can execute arbitrary code by providing malicious model checkpoints to vLLM due to unsafe pickle deserialization in weight loading.","user_interaction":"required","vuln_class":"deserialization"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"vllm","vendor":"vllm"}],"cvss":{"score":7.5,"severity":"high","source":"cna","vector":"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:H/I:H/A:H","version":"3.1"},"cwes":[{"id":"CWE-502","name":"Deserialization of Untrusted Data"}],"description":"vLLM is a library for LLM inference and serving. vllm/model_executor/weight_utils.py implements hf_model_weights_iterator to load the model checkpoint, which is downloaded from huggingface. It uses the torch.load function and the weights_only parameter defaults to False. When torch.load loads malicious pickle data, it will execute arbitrary code during unpickling. This vulnerability is fixed in v0.7.0.","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 allows a malicious model RCE by torch.load in hf_model_weights_iterator","id":"CVE-2025-24357","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":"vllm:vllm","products":["vllm:vllm"],"type":"deserialization","year":"2025"},"n_packages":3,"n_references":4,"next":{"headline":"gorilla/csrf CSRF vulnerability due to broken Referer validation","id":"CVE-2025-24358"},"packages":[{"ecosystem":"PyPI","fixed":["0.7.0"],"introduced":["0"],"last_affected":[],"package":"vllm","purl":null,"source":"GHSA-rh4j-5rhw-hr54"},{"ecosystem":"PyPI","fixed":["0.7.0"],"introduced":["0"],"last_affected":[],"package":"vllm","purl":"pkg:pypi/vllm","source":"GHSA-rh4j-5rhw-hr54"},{"ecosystem":"PyPI","fixed":["0.7.0"],"introduced":["0"],"last_affected":[],"package":"vllm","purl":"pkg:pypi/vllm","source":"PYSEC-2025-58"}],"prev":{"headline":"UDP traffic amplification via fastd's fast reconnect feature","id":"CVE-2025-24356"},"products":["vllm"],"published":"2025-01-27","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":"total"},"state":"PUBLISHED","updated":"2025-02-12","vendors":["vllm-project"]},"summary":"Attackers can execute arbitrary code by providing malicious model checkpoints to vLLM due to unsafe pickle deserialization in weight loading.","url":"https://insights.sbomify.com/CVE-2025-24357/"}