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.

Project Subscriptions

Vendors Products
Huggingface Subscribe
Tokenizers Subscribe
Advisories

No advisories yet.

Fixes

Solution

No solution given by the vendor.


Workaround

No workaround given by the vendor.

History

Fri, 04 Sep 2026 18:30:00 +0000

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'no', 'Exploitation': 'poc', 'Technical Impact': 'partial'}, 'version': '2.0.3'}


Fri, 04 Sep 2026 16:15:00 +0000

Type Values Removed Values Added
First Time appeared Huggingface
Huggingface tokenizers
Vendors & Products Huggingface
Huggingface tokenizers

Fri, 04 Sep 2026 14:45:00 +0000

Type Values Removed Values Added
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.
Title tokenizers BpeBuilder Buffer Overflow via merge token
Weaknesses CWE-787
References
Metrics cvssV3_1

{'score': 6.5, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H'}

cvssV4_0

{'score': 7.1, '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'}


Projects

Sign in to view the affected projects.

cve-icon MITRE

Status: PUBLISHED

Assigner: VulnCheck

Published:

Updated: 2026-09-04T17:49:42.263Z

Reserved: 2026-09-04T13:32:36.617Z

Link: CVE-2026-85670

cve-icon Vulnrichment

Updated: 2026-09-04T17:49:37.775Z

cve-icon NVD

Status : Received

Published: 2026-09-04T15:17:44.993

Modified: 2026-09-04T18:18:06.417

Link: CVE-2026-85670

cve-icon Redhat

No data.

cve-icon OpenCVE Enrichment

Updated: 2026-09-04T16:30:06Z

Weaknesses