{"answers":{"affected":"3 open source packages ship an affected version, including xgrammar. It affects 1 product.","exploited":"There is no known exploitation of CVE-2025-32381 in the wild and no public exploit code.","fix":"Upgrade xgrammar to 0.1.18 or later.","what":"CVE-2025-32381 is a medium-severity denial of service vulnerability in mlc-ai xgrammar, published on 9 Apr 2025. Any signed-in user can exploit it over the network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2025-32381 and fix it if it is affected.\n\nWhat it is: CVE-2025-32381 is a medium-severity denial of service vulnerability in mlc-ai xgrammar, published on 9 Apr 2025. Any signed-in user can exploit it over the network, with no action from the victim.\nExploitation: There is no known exploitation of CVE-2025-32381 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- xgrammar (PyPI): affected all versions; fixed in 0.1.18\n- xgrammar (PyPI): affected all versions; fixed in 0.1.18\n- xgrammar (PyPI): affected all versions; fixed in 0.1.18\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-2025-32381/ (Markdown: https://insights.sbomify.com/CVE-2025-32381/index.md)","id":"CVE-2025-32381","markdown":"https://insights.sbomify.com/CVE-2025-32381/index.md","name":"CVE-2025-32381","record":{"aliases":["GHSA-389x-67px-mjg3","PYSEC-2025-235"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["denial_of_service"],"network_reachable":"yes","non_default_config":false,"product_category":"XGrammar library","requires_auth":"low_privilege","summary":"An attacker can cause a denial of service by exhausting memory through unbounded caching of unique grammars in the XGrammar library.","user_interaction":"not_required","vuln_class":"denial_of_service"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[{"product":"xgrammar","vendor":"mlc-ai"}],"cvss":{"score":6.5,"severity":"medium","source":"cna","vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:H","version":"3.1"},"cwes":[{"id":"CWE-770","name":"Allocation of Resources Without Limits or Throttling"}],"description":"XGrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to 0.1.18, Xgrammar includes a cache for compiled grammars to increase performance with repeated use of the same grammar. This cache is held in memory. Since the cache is unbounded, a system making use of xgrammar can be abused to fill up a host's memory and case a denial of service. For example, sending many small requests to an LLM inference server with unique JSON schemas would eventually cause this denial of service to occur. This vulnerability is fixed in 0.1.18.","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":"Denial of Service by abusing xgrammar unbounded cache in memory","id":"CVE-2025-32381","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"denial_of_service","year":"2025"},"n_packages":3,"n_references":3,"next":{"headline":"Snowflake credentials logged by the Metabase backend","id":"CVE-2025-32382"},"packages":[{"ecosystem":"PyPI","fixed":["0.1.18"],"introduced":["0"],"last_affected":[],"package":"xgrammar","purl":null,"source":"GHSA-389x-67px-mjg3"},{"ecosystem":"PyPI","fixed":["0.1.18"],"introduced":["0"],"last_affected":[],"package":"xgrammar","purl":"pkg:pypi/xgrammar","source":"GHSA-389x-67px-mjg3"},{"ecosystem":"PyPI","fixed":["0.1.18"],"introduced":["0"],"last_affected":[],"package":"xgrammar","purl":"pkg:pypi/xgrammar","source":"PYSEC-2025-235"}],"prev":{"headline":"Apollo Router Query Validation Vulnerable to Excessive Resource Consumption via Named Fragment Processing","id":"CVE-2025-32380"},"products":["xgrammar"],"published":"2025-04-09","related":[{"cvss_score":8.7,"headline":"xgrammar: Multi-layer nesting causes DoS","id":"CVE-2026-25048","kev_date_added":null,"published":"2026-03-05"},{"cvss_score":7.7,"headline":"XGrammar affected by Denial of Service by infinite recursion grammars","id":"CVE-2025-57809","kev_date_added":null,"published":"2025-08-25"},{"cvss_score":6.9,"headline":"xgrammar vulnerable to denial of service by huge enum grammar","id":"CVE-2025-58446","kev_date_added":null,"published":"2025-09-06"}],"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":"partial"},"state":"PUBLISHED","updated":"2025-04-09","vendors":["mlc-ai"]},"summary":"An attacker can cause a denial of service by exhausting memory through unbounded caching of unique grammars in the XGrammar library.","url":"https://insights.sbomify.com/CVE-2025-32381/"}