{"action":"Upgrade llama.cpp to 5713+dfsg-1 or later.","affected":[{"fixed":"5713+dfsg-1","introduced":"0"}],"component":"llama.cpp","cve_ids":[],"ecosystem":"Debian","ecosystem_qualifier":"Debian:14","exploited":false,"fixed_versions":["5713+dfsg-1"],"id":"tcs_01M5NNZNX5XXJY3BKGJSNMTD30","modified_at":"2026-09-01T20:05:53.376526068Z","published_at":"2025-06-17T20:15:32.437Z","references":["https://osv.dev/vulnerability/DEBIAN-CVE-2025-49847","https://security-tracker.debian.org/tracker/CVE-2025-49847"],"severity":{"label":"high","score":8.8},"sources":[{"source":"osv","source_id":"DEBIAN-CVE-2025-49847","url":"https://osv.dev/vulnerability/DEBIAN-CVE-2025-49847"}],"summary":"llama.cpp is an inference of several LLM models in C/C++. Prior to version b5662, an attacker‐supplied GGUF model vocabulary can trigger a buffer overflow in llama.cpp’s vocabulary‐loading code. Speci"}