Anthropic Says Claude Hacked Into 3 Organizations During Cybersecurity Tests

In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real-world organizations during third-party evaluations...

OpenAI Agent Used Exposed Credentials Across Four Services During Hugging Face Breach

OpenAI on Tuesday revealed the rogue artificial intelligence AI agent that escaped its sealed evaluation environment and broke into Hugging Face's production environment also hacked multiple third-party accounts and services as part of the attack. The latest disclosure shows that the security...

JFrog Confirms OpenAI Models Exploited Artifactory Zero-Day Before Hugging Face Breach

JFrog has confirmed that OpenAI models exploited a zero-day in self-hosted Artifactory while trying to reach the open internet from a sealed evaluation environment. Artifactory is JFrog's software repository manager. OpenAI says the models then escalated privileges and moved laterally until they...

Hugging Face Has a Deepfake Nudes Problem

Researchers tested top image editing models on Hugging Face and found they could easily create explicit deepfakes—and 1,000 image editing prompts show how people use the software...

⚡ Weekly Recap: Rogue AI Agents, Check Point Exploit, Slopsquatting, ClickFix Lures and More

Monday starts with the usual promise that everything is under control. Then the logs wake up. This week, trusted tools crossed lines, old flaws found new work, exposed systems stayed exposed, and attackers kept hiding inside normal-looking services. Nothing looked strange at first. That helped...

CVE-2026-65010

A flaw was found in Hugging Face Datasets through 5.00 in Extractor.extract. When archive contents are extracted to predictable output paths, the extractor follows pre-planted symlinks instead of confining writes to the intended directory. A local attacker who can place those symlinks can redirec...

OpenAI’s agent escaped its sandbox during a security test

During an internal OpenAI security evaluation, a chain of AI models escaped its sandbox, reached the internet, and then accessed Hugging Face infrastructure to complete the test objective. OpenAI is a leading artificial intelligence AI research and deployment company. Its best-known product is...

OpenAI Models Breached Hugging Face During Internal Cyber Test

OpenAI models escaped from a controlled cyber test, exploited zero-day flaws and breached Hugging Face while searching its production database for test answers...

OpenAI Says Its AI Models Escaped Sandbox, Targeted Hugging Face to Cheat Benchmark

OpenAI on Tuesday said a combination of its artificial intelligence AI models, including GPT-5.6 Sol and an "even more capable pre-release model," was behind the security incident that targeted Hugging Face's production infrastructure last week. The AI company said the models were operating with...

World's Largest AI Model Repository Hugging Face Breached by Autonomous AI Agent

In an ironic twist, open-source artificial intelligence AI platform Hugging Face revealed that it was the victim of a hack perpetrated by an autonomous AI agent system. The company said it detected and responded to the incident targeting its production infrastructure earlier last week. "We...

PYSEC-2026-3066 Hugging Face Smolagents has an Injection issue

A weakness has been identified in huggingface smolagents 1.25.0.dev0. This affects the function evaluateaugassign/evaluatecall/evaluatewith of the file src/smolagents/localpythonexecutor.py of the component Incomplete Fix CVE-2025-9959. This manipulation causes code injection. It is possible to...

PYSEC-2026-3067 Hugging Face Smolagents has a Server-Side Request Forgery issue

A weakness has been identified in huggingface smolagents 1.24.0. Impacted is the function requests.get/requests.post of the component LocalPythonExecutor. Executing a manipulation can lead to server-side request forgery. It is possible to launch the attack remotely. The exploit has been made...

PYSEC-2026-1930 Hugging Face Smolagents XPath injection vulnerability in the search_item_ctrl_f function

Hugging Face Smolagents version 1.20.0 contains an XPath injection vulnerability in the searchitemctrlf function located in src/smolagents/visionwebbrowser.py. The function constructs an XPath query by directly concatenating user-supplied input into the XPath expression without proper sanitizatio...

PYSEC-2026-1980 Hugging Face Transformers vulnerable to Regular Expression Denial of Service (ReDoS) in the AdamWeightDecay optimizer

The huggingface/transformers library, versions prior to 4.53.0, is vulnerable to Regular Expression Denial of Service ReDoS in the AdamWeightDecay optimizer. The vulnerability arises from the douseweightdecay method, which processes user-controlled regular expressions in the includeinweightdecay...

PYSEC-2026-1988 Hugging Face Transformers library has Regular Expression Denial of Service

A Regular Expression Denial of Service ReDoS vulnerability was discovered in the Hugging Face Transformers library, specifically within the normalizenumbers method of the EnglishNormalizer class. This vulnerability affects versions up to 4.52.4 and is fixed in version 4.53.0. The issue arises fro...

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...

PYSEC-2026-1983 Hugging Face Transformers Regular Expression Denial of Service (ReDoS) vulnerability

A Regular Expression Denial of Service ReDoS vulnerability exists in the Hugging Face Transformers library, specifically in the converttfweightnametoptweightname function. This function, responsible for converting TensorFlow weight names to PyTorch format, uses a regex pattern /^/^// that can be...

Malicious code in logger-daemon-regex (npm)

The npm package logger-daemon-regex is a full-spectrum information stealer and remote-control agent disguised as a "Node.js integration layer for Autodesk Forge" all bin names are forge-. A postinstall lifecycle hook chains five scripts postinstall-clipboard-event, ensure-dist,...

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...

EUVD-2026-40311

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...