{"action":"Upgrade ggml to 0.0~git20250711.b6d2ebd-1 or later.","affected":[{"introduced":"0"}],"component":"ggml","cve_ids":[],"ecosystem":"Debian","ecosystem_qualifier":"Debian:14","exploited":false,"fixed_versions":["0.0~git20250711.b6d2ebd-1"],"id":"tcs_01M5NP14BBTD30ND25VVMJB8F2","modified_at":"2026-09-01T20:05:54.366162310Z","published_at":"2025-07-10T20:15:27.523Z","references":["https://osv.dev/vulnerability/DEBIAN-CVE-2025-53630","https://security-tracker.debian.org/tracker/CVE-2025-53630"],"severity":{"label":"unknown"},"sources":[{"source":"osv","source_id":"DEBIAN-CVE-2025-53630","url":"https://osv.dev/vulnerability/DEBIAN-CVE-2025-53630"}],"summary":"llama.cpp is an inference of several LLM models in C/C++. Integer Overflow in the gguf_init_from_file_impl function in ggml/src/gguf.cpp can lead to Heap Out-of-Bounds Read/Write. This vulnerability i"}