{"id":"CVE-2026-47750","aliases":["EUVD-2026-37198","GHSA-v37x-jwp7-mcvc"],"status":"published","title":"stable-diffusion.cpp: Heap buffer overflow in GLOBAL opcode parsing for PyTorch checkpoint files","description":"stable-diffusion.cpp is a pure C/C++ library for running diffusion model (Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more) inference. In versions prior to master-584-0a7ae07,  the pickle .ckpt parser in src/model.cpp contained a heap buffer overflow vulnerability in the GLOBAL opcode handler. The issue was caused by missing validation when searching for newline-delimited fields. A crafted .ckpt file without the expected newline could cause the parser to use -1 as a copy length, resulting in immediate heap corruption. The attack requires the victim or application to load a .ckpt file from an untrusted source, such as a downloaded model from a model sharing site. The issue has been resolved in version master-584-0a7ae07. If developers are unable to immediately update their applications they can work around this issue by following these instructions: do not load .ckpt checkpoint files from untrusted sources, and prefer trusted model sources and safer formats such as .safetensors where possible.","severity":{"version":"3.1","score":7.8,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-12","score":0.0018,"percentile":0.07672,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-787"],"published":"2026-06-16T18:17:41Z","modified":"2026-10-28T10:55:40Z","products":[{"vendor":"leejet","product":"stable-diffusion.cpp"}],"references":[{"url":"https://github.com/leejet/stable-diffusion.cpp/security/advisories/GHSA-v37x-jwp7-mcvc","tags":["x_refsource_CONFIRM","exploit","Exploit","Mitigation","Vendor Advisory","advisory"]},{"url":"https://github.com/leejet/stable-diffusion.cpp/pull/1443","tags":["x_refsource_MISC","Issue Tracking","Patch","fix"]},{"url":"https://github.com/leejet/stable-diffusion.cpp/commit/0a7ae07f948eff4611968a65a22bd7c7031ad74f","tags":["x_refsource_MISC","Patch","fix"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/47xxx/CVE-2026-47750.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-47750","tags":["advisory"]}],"sources":{"cve":[{"id":"CVE-2026-47750","title":"stable-diffusion.cpp: Heap buffer overflow in GLOBAL opcode parsing for PyTorch checkpoint files","description":"stable-diffusion.cpp is a pure C/C++ library for running diffusion model (Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more) inference. In versions prior to master-584-0a7ae07,  the pickle .ckpt parser in src/model.cpp contained a heap buffer overflow vulnerability in the GLOBAL opcode handler. The issue was caused by missing validation when searching for newline-delimited fields. A crafted .ckpt file without the expected newline could cause the parser to use -1 as a copy length, resulting in immediate heap corruption. The attack requires the victim or application to load a .ckpt file from an untrusted source, such as a downloaded model from a model sharing site. The issue has been resolved in version master-584-0a7ae07. If developers are unable to immediately update their applications they can work around this issue by following these instructions: do not load .ckpt checkpoint files from untrusted sources, and prefer trusted model sources and safer formats such as .safetensors where possible.","status":"published","published":"2026-06-16T18:17:41.349Z","modified":"2026-06-17T13:58:25.254Z","cvss":[{"version":"3.1","score":7.8,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high","assessor":"cna"}],"cwes":["CWE-787"],"updated_at":"2026-11-02T13:36:40.478484Z"}],"euvd":[{"id":"EUVD-2026-37198","description":"stable-diffusion.cpp is a pure C/C++ library for running diffusion model (Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more) inference. In versions prior to master-584-0a7ae07,  the pickle .ckpt parser in src/model.cpp contained a heap buffer overflow vulnerability in the GLOBAL opcode handler. The issue was caused by missing validation when searching for newline-delimited fields. A crafted .ckpt file without the expected newline could cause the parser to use -1 as a copy length, resulting in immediate heap corruption. The attack requires the victim or application to load a .ckpt file from an untrusted source, such as a downloaded model from a model sharing site. The issue has been resolved in version master-584-0a7ae07. If developers are unable to immediately update their applications they can work around this issue by following these instructions: do not load .ckpt checkpoint files from untrusted sources, and prefer trusted model sources and safer formats such as .safetensors where possible.","status":"published","published":"2026-06-16T18:17:41Z","modified":"2026-06-17T13:58:25Z","cvss":[{"version":"3.1","score":7.8,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high"}],"updated_at":"2026-11-02T18:20:38.883875Z"}],"nvd":[{"id":"CVE-2026-47750","description":"stable-diffusion.cpp is a pure C/C++ library for running diffusion model (Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more) inference. In versions prior to master-584-0a7ae07,  the pickle .ckpt parser in src/model.cpp contained a heap buffer overflow vulnerability in the GLOBAL opcode handler. The issue was caused by missing validation when searching for newline-delimited fields. A crafted .ckpt file without the expected newline could cause the parser to use -1 as a copy length, resulting in immediate heap corruption. The attack requires the victim or application to load a .ckpt file from an untrusted source, such as a downloaded model from a model sharing site. The issue has been resolved in version master-584-0a7ae07. If developers are unable to immediately update their applications they can work around this issue by following these instructions: do not load .ckpt checkpoint files from untrusted sources, and prefer trusted model sources and safer formats such as .safetensors where possible.","status":"published","published":"2026-06-16T20:16:44.413Z","modified":"2026-10-25T23:10:00.167Z","cvss":[{"version":"3.1","score":7.8,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high","assessor":"secondary"}],"cwes":["CWE-787"],"updated_at":"2026-11-02T14:12:24.19758Z"}],"osv":[{"id":"CVE-2026-47750","title":"stable-diffusion.cpp: Heap buffer overflow in GLOBAL opcode parsing for PyTorch checkpoint files","description":"stable-diffusion.cpp is a pure C/C++ library for running diffusion model (Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more) inference. In versions prior to master-584-0a7ae07,  the pickle .ckpt parser in src/model.cpp contained a heap buffer overflow vulnerability in the GLOBAL opcode handler. The issue was caused by missing validation when searching for newline-delimited fields. A crafted .ckpt file without the expected newline could cause the parser to use -1 as a copy length, resulting in immediate heap corruption. The attack requires the victim or application to load a .ckpt file from an untrusted source, such as a downloaded model from a model sharing site. The issue has been resolved in version master-584-0a7ae07. If developers are unable to immediately update their applications they can work around this issue by following these instructions: do not load .ckpt checkpoint files from untrusted sources, and prefer trusted model sources and safer formats such as .safetensors where possible.","status":"published","published":"2026-06-16T18:17:41.349Z","modified":"2026-10-28T10:55:40.621281588Z","cvss":[{"version":"3.1","score":7.8,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H","level":"high"}],"cwes":["CWE-787"],"updated_at":"2026-11-02T15:45:06.231145Z"}]}}