{"id":"CVE-2026-85670","aliases":[],"url":"https://o3.security/vulnerability/CVE-2026-85670","summary":"tokenizers (Hugging Face) is affected by an out-of-bounds buffer access in BpeBuilder::build (tokenizers/src/models/bpe/model.rs). When loading a tokenizer.json via Tokenizer::from_file/from_str,…","details":"tokenizers (Hugging Face) is affected by an out-of-bounds buffer access in BpeBuilder::build (tokenizers/src/models/bpe/model.rs). When loading a tokenizer.json via Tokenizer::from_file/from_str, the builder sizes a scratch buffer to the longest vocabulary key, then writes each concatenated merge rule into it. A merge whose concatenated token exceeds the longest vocabulary key overruns the buffer, which Rust turns into a panic that aborts the process in Rust and FFI embeddings. This occurs at load time with no encoding required, so an attacker who supplies a crafted tokenizer.json can cause a denial of service. A secondary defect at the same location can cause a usize underflow (panic in debug, potential memory corruption in release) when continuing_subword_prefix is set and a merge token is shorter than the prefix. Observed in version 0.23.1.","published":"2026-09-04T15:17:44.993","modified":"2026-09-04T15:17:44.993","cvss":{"score":6.5,"severity":"MEDIUM","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H"},"epss":null,"cisaKev":null,"exploitsKnown":null,"affectedPackages":[],"fix":null,"references":[{"type":"WEB","url":"https://github.com/huggingface/tokenizers"},{"type":"WEB","url":"https://github.com/huggingface/tokenizers/blob/v0.23.2/tokenizers/src/models/bpe/model.rs"},{"type":"WEB","url":"https://github.com/huggingface/tokenizers/issues/2094"},{"type":"WEB","url":"https://www.vulncheck.com/advisories/tokenizers-bpebuilder-buffer-overflow-via-merge-token"}],"provenance":{"sources":["OSV.dev","NVD","FIRST.org (EPSS)"],"lastVerified":"2026-09-04T15:17:44.993"}}