CVE-2026-85670 PUBLISHED

tokenizers BpeBuilder Buffer Overflow via merge token

Assigner: VulnCheck
Reserved: 04.09.2026 Published: 04.09.2026 Updated: 04.09.2026

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.

Metrics

CVSS Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:N/VI:N/VA:H/SC:N/SI:N/SA:N
CVSS Score: 7.1

Product Status

Vendor huggingface
Product tokenizers
Versions Default: unaffected
  • affected from 0 to 0.23.2 (incl.)

Credits

  • George Chen finder

References

Problem Types

  • Out-of-bounds Write CWE