{"id":"CVE-2026-27940","aliases":["DEBIAN-CVE-2026-27940","EUVD-2026-11605","GHSA-3p4r-fq3f-q74v","UBUNTU-CVE-2026-27940"],"status":"published","title":"llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix","description":"llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.","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":"2026-11-11","score":0.00212,"percentile":0.11647,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":true,"fix_available":true},"cwes":["CWE-122","CWE-190"],"published":"2026-03-12T16:39:37Z","modified":"2026-10-28T11:10:04Z","exploits":[{"source":"pocgithub","id":"ngtuonghung/CVE-2026-27940","title":"ngtuonghung/CVE-2026-27940","date":"2026-03-29","url":"https://github.com/ngtuonghung/CVE-2026-27940"}],"fixes":[{"ecosystem":"Debian:14","package":"llama.cpp","fixed_in":["8461+dfsg-1"],"sources":["osv"]}],"affected":[{"source":"osv","ecosystem":"Debian:14","package":"llama.cpp","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"8461+dfsg-1"}]}],"versions":["5151+dfsg-1~exp2","5151+dfsg-1~exp3","5318+dfsg-1","5318+dfsg-2","5713+dfsg-1","5760+dfsg-1","5760+dfsg-2","5760+dfsg-3","5760+dfsg-4","5882+dfsg-1","5882+dfsg-2","5882+dfsg-3","5882+dfsg-3~exp1","5882+dfsg-3~exp2","5882+dfsg-3~exp3","5882+dfsg-4","6641+dfsg-1","6641+dfsg-2","6641+dfsg-3","7593+dfsg-1","7593+dfsg-2","7593+dfsg-3","7965+dfsg-1","8064+dfsg-1","8064+dfsg-2"]},{"source":"osv","ecosystem":"Ubuntu:25.10","package":"llama.cpp","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["5318+dfsg-1","5318+dfsg-2","5713+dfsg-1","5760+dfsg-1","5760+dfsg-3","5760+dfsg-4","5882+dfsg-2"]},{"source":"osv","ecosystem":"Ubuntu:26.10","package":"llama.cpp","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["8681+dfsg-1","9721+dfsg-1ubuntu1","10438+dfsg-1","10438+dfsg-1ubuntu1"]},{"source":"osv","ecosystem":"Ubuntu:26.04:LTS","package":"llama.cpp","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["5882+dfsg-2","8064+dfsg-1ubuntu1","8681+dfsg-1"]}],"products":[{"vendor":"ggml","product":"llama.cpp"},{"vendor":"ggml-org","product":"llama.cpp"}],"references":[{"url":"https://github.com/ggml-org/llama.cpp/security/advisories/GHSA-3p4r-fq3f-q74v","tags":["x_refsource_CONFIRM","Exploit","Vendor Advisory","advisory"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/27xxx/CVE-2026-27940.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-27940","tags":["advisory"]},{"url":"https://security-tracker.debian.org/tracker/CVE-2026-27940","tags":["advisory"]},{"url":"https://ubuntu.com/security/CVE-2026-27940","tags":["report"]},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-27940","tags":["report"]}],"sources":{"cve":[{"id":"CVE-2026-27940","title":"llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix","description":"llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.","status":"published","published":"2026-03-12T16:39:37.463Z","modified":"2026-03-14T03:55:24.463Z","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-122","CWE-190"],"updated_at":"2026-11-02T14:19:49.199185Z"}],"euvd":[{"id":"EUVD-2026-11605","description":"llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.","status":"published","published":"2026-03-12T16:39:37Z","modified":"2026-03-14T03:55:24Z","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":"2026-11-02T19:25:35.010093Z"}],"nvd":[{"id":"CVE-2026-27940","description":"llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.","status":"published","published":"2026-03-12T17:16:49.92Z","modified":"2026-06-17T10:27:56.667Z","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-122","CWE-190"],"updated_at":"2026-11-02T14:12:09.358914Z"}],"osv":[{"id":"CVE-2026-27940","title":"llama.cpp has a Heap Buffer Overflow via Integer Overflow in `mem_size` Calculation — Bypass of CVE-2025-53630 Fix","description":"llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.","status":"published","published":"2026-03-12T16:39:37.463Z","modified":"2026-10-28T11:10:04.87649248Z","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-122","CWE-190"],"updated_at":"2026-11-02T15:45:00.180685Z"},{"id":"DEBIAN-CVE-2026-27940","description":"llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.","status":"published","published":"2026-03-12T17:16:49.92Z","modified":"2026-10-01T03:03:02.351728434Z","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":"2026-11-02T15:45:53.877573Z"},{"id":"UBUNTU-CVE-2026-27940","description":"llama.cpp is an inference of several LLM models in C/C++. Prior to b8146, the gguf_init_from_file_impl() in gguf.cpp is vulnerable to an Integer overflow, leading to an undersized heap allocation. Using the subsequent fread() writes 528+ bytes of attacker-controlled data past the buffer boundary. This is a bypass of a similar bug in the same file - CVE-2025-53630, but the fix overlooked some areas. This vulnerability is fixed in b8146.","status":"published","published":"2026-03-12T17:16:00Z","modified":"2026-10-17T12:56:18.017931374Z","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":"2026-11-02T16:56:08.726452Z"}]}}