CVEvulnerability
CVE-2026-85670
7.1 HIGH
Official page ↗
- Status
- Awaiting Analysis
- Published
- 2026-09-04
- Last modified
- 2026-09-24
- Assigner
- [email protected]
- CVSS 4.0 ([email protected])
- 7.1 HIGH — 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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
- CVSS 3.1 ([email protected])
- 6.5 MEDIUM — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H
- Weaknesses
- CWE-787
Description
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.
Related
Weakness · CWE (1)
- CWE-787 Out-of-bounds Write weakness
References
- https://github.com/huggingface/tokenizers github.com
- https://github.com/huggingface/tokenizers/blob/v0.23.2/tokenizers/src/models/bpe/model.rs github.com
- https://github.com/huggingface/tokenizers/issues/2094 github.com
- https://www.vulncheck.com/advisories/tokenizers-bpebuilder-buffer-overflow-via-merge-token www.vulncheck.com
- https://github.com/huggingface/tokenizers/issues/2094 github.com