{"action":"Upgrade llama.cpp to 8461+dfsg-1 or later.","affected":[{"fixed":"8461+dfsg-1","introduced":"0"}],"component":"llama.cpp","cve_ids":[],"ecosystem":"Debian","ecosystem_qualifier":"Debian:14","exploited":false,"fixed_versions":["8461+dfsg-1"],"id":"tcs_01M5NRG7QGTJPPKVAMNGP7776V","modified_at":"2026-10-01T03:03:02.351728434Z","published_at":"2026-03-12T17:16:49.920Z","references":["https://osv.dev/vulnerability/DEBIAN-CVE-2026-27940","https://security-tracker.debian.org/tracker/CVE-2026-27940"],"severity":{"label":"high","score":7.8},"sources":[{"source":"osv","source_id":"DEBIAN-CVE-2026-27940","url":"https://osv.dev/vulnerability/DEBIAN-CVE-2026-27940"}],"summary":"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. Usi"}