{"action":"Upgrade llama.cpp to 8611+dfsg-1 or later.","affected":[{"fixed":"8611+dfsg-1","introduced":"0"}],"component":"llama.cpp","cve_ids":[],"ecosystem":"Debian","ecosystem_qualifier":"Debian:14","exploited":false,"fixed_versions":["8611+dfsg-1"],"id":"tcs_01M5NRRZVTMX4E8QEQZ5KHVNEM","modified_at":"2026-10-27T09:47:33.491021756Z","published_at":"2026-04-01T18:16:29.687Z","references":["https://osv.dev/vulnerability/DEBIAN-CVE-2026-34159","https://security-tracker.debian.org/tracker/CVE-2026-34159"],"severity":{"label":"critical","score":9.8},"sources":[{"source":"osv","source_id":"DEBIAN-CVE-2026-34159","url":"https://osv.dev/vulnerability/DEBIAN-CVE-2026-34159"}],"summary":"llama.cpp is an inference of several LLM models in C/C++. Prior to version b8492, the RPC backend's deserialize_tensor() skips all bounds validation when a tensor's buffer field is 0. An unauthenticat"}