Hugging Face tokenizers up to 0.23.2 BpeBuilder model.rs BpeBuilder::build buffer overflow

CVSS Meta Temp Score
CVSS is a standardized scoring system to determine possibilities of attacks. The Temp Score considers temporal factors like disclosure, exploit and countermeasures. The unique Meta Score calculates the average score of different sources to provide a normalized scoring system.
Current Exploit Price (≈)
Our analysts are monitoring exploit markets and are in contact with vulnerability brokers. The range indicates the observed or calculated exploit price to be seen on exploit markets. A good indicator to understand the monetary effort required for and the popularity of an attack.
CTI Interest Score
Our Cyber Threat Intelligence team is monitoring different web sites, mailing lists, exploit markets and social media networks. The CTI Interest Score identifies the interest of attackers and the security community for this specific vulnerability in real-time. A high score indicates an elevated risk to be targeted for this vulnerability.
5.3$0-$5k1.23-

Summaryinfo

A vulnerability was found in Hugging Face tokenizers up to 0.23.2. It has been classified as problematic. Affected is the function BpeBuilder::build of the file tokenizers/src/models/bpe/model.rs of the component BpeBuilder. The manipulation leads to buffer overflow. This vulnerability is uniquely identified as CVE-2026-85670. The attack is possible to be carried out remotely. No exploit exists.

Detailsinfo

A vulnerability, which was classified as problematic, has been found in Hugging Face tokenizers up to 0.23.2. This issue affects the function BpeBuilder::build of the file tokenizers/src/models/bpe/model.rs of the component BpeBuilder. The manipulation with an unknown input leads to a buffer overflow vulnerability. Using CWE to declare the problem leads to CWE-120. The product copies an input buffer to an output buffer without verifying that the size of the input buffer is less than the size of the output buffer, leading to a buffer overflow. Impacted is availability. The summary by CVE is:

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.

The advisory is shared at github.com. The identification of this vulnerability is CVE-2026-85670 since 09/04/2026. The exploitation is known to be easy. The attack may be initiated remotely. No form of authentication is needed for a successful exploitation. It demands that the victim is doing some kind of user interaction. Technical details are known, but no exploit is available. The price for an exploit might be around USD $0-$5k at the moment (estimation calculated on 09/04/2026).

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Productinfo

Vendor

Name

Version

CPE 2.3info

CPE 2.2info

CVSSv4info

VulDB Vector: 🔒
VulDB Reliability: 🔍

CNA CVSS-B Score: 🔒
CNA CVSS-BT Score: 🔒
CNA Vector: 🔒

CVSSv3info

VulDB Meta Base Score: 5.4
VulDB Meta Temp Score: 5.3

VulDB Base Score: 4.3
VulDB Temp Score: 4.2
VulDB Vector: 🔒
VulDB Reliability: 🔍

CNA Base Score: 6.5
CNA Vector (VulnCheck): 🔒

CVSSv2info

AVACAuCIA
💳💳💳💳💳💳
💳💳💳💳💳💳
💳💳💳💳💳💳
VectorComplexityAuthenticationConfidentialityIntegrityAvailability
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock
UnlockUnlockUnlockUnlockUnlockUnlock

VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍

Exploitinginfo

Class: Buffer overflow
CWE: CWE-120 / CWE-119
CAPEC: 🔒
ATT&CK: 🔒

Physical: No
Local: No
Remote: Yes

Availability: 🔒
Status: Not defined
Price Prediction: 🔍
Current Price Estimation: 🔒

0-DayUnlockUnlockUnlockUnlock
TodayUnlockUnlockUnlockUnlock

Threat Intelligenceinfo

Interest: 🔍
Active Actors: 🔍
Active APT Groups: 🔍

Countermeasuresinfo

Recommended: no mitigation known
Status: 🔍

0-Day Time: 🔒

Timelineinfo

09/04/2026 Advisory disclosed
09/04/2026 +0 days CVE reserved
09/04/2026 +0 days VulDB entry created
09/04/2026 +0 days VulDB entry last update

Sourcesinfo

Advisory: github.com
Status: Not defined

CVE: CVE-2026-85670 (🔒)
GCVE (CVE): GCVE-0-2026-85670
GCVE (VulDB): GCVE-100-398837

Entryinfo

Created: 09/04/2026 17:07
Changes: 09/04/2026 17:07 (76)
Complete: 🔍
Cache ID: 216::103

If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Discussion

No comments yet. Languages: en.

Please log in to comment.

Interested in the pricing of exploits?

See the underground prices here!