PT-2026-59682

A vulnerability was detected in sgl-project SGLang up to 0.5.9. Impacted is the function get tokenizer of the file python/sglang/srt/utils/hf transformers utils.py of the component HuggingFace Transformer Handler. The manipulation results in deserialization. The attack can be executed remotely. A...

MAL-2026-10163 Malicious code in llama-tokenizer (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector b22305b1026f27be6d5b78dc19f7db7a05cc9d1818b7ebc7cda0fce92431aa02 This package typosquats llama-tokenizer-js. On require, index.js reconstructs a host and URL path from String.fromCharCode numeric arrays, downloads ...

Malicious code in llama-tokenizer (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector b22305b1026f27be6d5b78dc19f7db7a05cc9d1818b7ebc7cda0fce92431aa02 This package typosquats llama-tokenizer-js. On require, index.js reconstructs a host and URL path from String.fromCharCode numeric arrays, downloads ...

PYSEC-2026-1981 Hugging Face Transformers is vulnerable to ReDoS through its MarianTokenizer

A Regular Expression Denial of Service ReDoS vulnerability was discovered in the Hugging Face Transformers library, specifically affecting the MarianTokenizer's removelanguagecode method. This vulnerability is present in version 4.52.4 and has been fixed in version 4.53.0. The issue arises from...

Hugging Face Transformers is vulnerable to ReDoS through its MarianTokenizer

A Regular Expression Denial of Service ReDoS vulnerability was discovered in the Hugging Face Transformers library, specifically affecting the MarianTokenizer's removelanguagecode method. This vulnerability is present in version 4.52.4 and has been fixed in version 4.53.0. The issue arises from...

Transformers Regular Expression Denial of Service (ReDoS) vulnerability

A Regular Expression Denial of Service ReDoS vulnerability was identified in the huggingface/transformers library, specifically in the file tokenizationgptneoxjapanese.py of the GPT-NeoX-Japanese model. The vulnerability occurs in the SubWordJapaneseTokenizer class, where regular expressions...

PYSEC-2026-2022 phi4mm: Quadratic Time Complexity in Input Token Processing​ leads to denial of service

Summary A critical performance vulnerability has been identified in the input preprocessing logic of the multimodal tokenizer. The code dynamically replaces placeholder tokens e.g., , with repeated tokens based on precomputed lengths. Due to ​​inefficient list concatenation operations​​, the...

Exploit for Inclusion of Functionality from Untrusted Control Sphere in Hiyouga Llama-Factory

CVE-2026-58116 — LLaMA-Factory WebUI RCE via trustremotecod...

CVE-2026-58116

CVE-2026-58116 affects LLaMA-Factory up to version 0.9.5. A remote code execution vulnerability exists when a malicious model path is supplied via WebUI Chat/Training interfaces; unvalidated input is passed to AutoTokenizer.from_pretrained() and AutoModel.from_pretrained() with trust_remote_code=...

CVE-2026-58116 LLaMA-Factory 0.9.5 Remote Code Execution via WebUI Model Path

LLaMA-Factory through 0.9.5 contains a remote code execution vulnerability that allows attackers with WebUI access to execute arbitrary Python code by supplying a malicious model path in the Chat or Training interfaces. The application passes user-supplied model path input unvalidated into...

CVE-2026-58116

LLaMA-Factory through 0.9.5 contains a remote code execution vulnerability that allows attackers with WebUI access to execute arbitrary Python code by supplying a malicious model path in the Chat or Training interfaces. The application passes user-supplied model path input unvalidated into...

CVE-2026-58116 LLaMA-Factory 0.9.5 Remote Code Execution via WebUI Model Path

LLaMA-Factory through 0.9.5 contains a remote code execution vulnerability that allows attackers with WebUI access to execute arbitrary Python code by supplying a malicious model path in the Chat or Training interfaces. The application passes user-supplied model path input unvalidated into...

PYSEC-2026-387 LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint

BerriAI/litellm is vulnerable to Server-Side Template Injection SSTI via the /completions endpoint. The vulnerability arises from the hfchattemplate method processing the chattemplate parameter from the tokenizerconfig.json file through the Jinja template engine without proper sanitization...

LiteLLM has Server-Side Template Injection vulnerability in /completions endpoint

BerriAI/litellm is vulnerable to Server-Side Template Injection SSTI via the /completions endpoint. The vulnerability arises from the hfchattemplate method processing the chattemplate parameter from the tokenizerconfig.json file through the Jinja template engine without proper sanitization...

PT-2026-53472

BerriAI/litellm is vulnerable to Server-Side Template Injection SSTI via the /completions endpoint. The vulnerability arises from the hf chat template method processing the chat template parameter from the tokenizer config.json file through the Jinja template engine without proper sanitization...

Allocation of Resources Without Limits or Throttling

Overview Affected versions of this package are vulnerable to Allocation of Resources Without Limits or Throttling in tokenizer.rb process. An attacker can cause excessive CPU and memory consumption by submitting CSS strings with large numeric exponents. Remediation Upgrade crass to version 1.0.7 ...

ngxray Vulnerability Scanner

ngxray is a static vulnerability scanner for nginx configurations. It parses configs with nginx's own tokenizer and matches against declarative JSON rules to detect known CVEs in rewrite/script engine directive patterns...

[SECURITY] Fedora 44 Update: sentencepiece-0.2.1-1.fc44

The SentencePiece is an unsupervised text tokenizer for Neural Network-based text generation. It is an unsupervised text tokenizer and detokenizer mainly for Neural Network-based text generation systems where the vocabulary size is predetermined prior to the neural model training. SentencePiece...

CVE-2026-47117

OpenMed before 1.5.2 contains a remote code execution vulnerability in the PII privacy-filter model loading path. The privacy-filter dispatcher used broad substring matching on the user-supplied modelname parameter, allowing a value such as attacker/foo-privacy-filter-bar to route through a path...

CVE-2026-47117

OpenMed before 1.5.2 contains a remote code execution vulnerability in the PII privacy-filter model loading path. The privacy-filter dispatcher used broad substring matching on the user-supplied modelname parameter, allowing a value such as attacker/foo-privacy-filter-bar to route through a path...