PT-2026-85563 · Hugging Face · Tokenizers
CVSS v3.1
6.5
Medium
| Vector | AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H |
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.
Fix
Memory Corruption
Found an issue in the description? Have something to add? Feel free to write us 👾
Weakness Enumeration
Related Identifiers
Affected Products
Tokenizers