Affected Technology
AI Agents incidents
Security concerns related to AI agents
Adobe Commerce Backdoor Vulnerability
Attackers are exploiting a new unpatched vulnerability in Magento Open Source and Adobe Commerce that lets them run malicious code on an online store's server without logging in, Dutch e-commerce security company Sansec said in an advisory published on September 5. Sansec, which discovered the flaw and named it StyleSmuggler, said attacks started on September 4. "Sansec is
Claude Security Incident
A fake Web3 accelerator has been observed pushing information stealers and backdoors to Windows and macOS systems using malicious npm packages under the pretext of offering free artificial intelligence (AI) credits for Anthropic Claude and Google Gemini, coding tools, and security audits. "The tools delivered information-stealing malware and backdoors for macOS and Windows machines," Elastic
Google API Keys Data Exposure
An intruder reached a legacy system at OpenCode on the night of October 16 and may have exposed the third-party AI provider keys that users had saved in OpenCode Console, the company said. Console is OpenCode's optional hosted service: a workspace saves its own OpenAI, Anthropic, or Google key there, and Console uses that key to call the provider so team members can use the models without
Anthropic Remote Code Execution Vulnerability
Warning Over High-Risk Security Vulnerabilities in Widely Used LLM Gat Infosecurity Magazine
PyTorch Remote Code Execution Vulnerability
A vulnerability in the HuggingFace Transformers library, specifically in the `Trainer` class, allows for arbitrary code execution. The `_load_rng_state()` method in `src/transformers/trainer.py` at line 3059 calls `torch.load()` without the `weights_only=True` parameter. This issue affects all versions of the library supporting `torch>=2.2` when used with PyTorch versions below 2.6, as the `safe_globals()` context manager provides no protection in these versions. An attacker can exploit this vulnerability by supplying a malicious checkpoint file, such as `rng_state.pth`, which can execute arbitrary code when loaded. The issue is resolved in version v5.0.0rc3.
OpenAI AI Security Breach Triggers 14-State Legal Reckoning
OpenAI's new GPT-5.5-Cyber tops Claude Mythos 5 in vulnerability benchmark Neowin
Easy Part Authentication Bypass
The bug was simple: the login let you choose where your sign-in code went. Proving it on a live website was the hard part. TL;DR During an authorized assessment, an AI pentesting agent found a critical authentication bypass on a major insurer's production website, on its own. One login request let the user choose where the one-time passcode went. The attack was the easy part. Proving it
Gemini Credential Compromise
Credential-stealing malware detected within minutes of npm release, but impact remains unknown
Chinese AI Penetration Tool Traces Found on Hacking Server in South Korea's Shinhan Bank Breach
Chinese AI Penetration Tool Traces Found on Hacking Server in South Korea's Shinhan Bank Breach finance.biggo.com
Agent Just Breached Remote Code Execution Vulnerability
An Autonomous AI Agent Just Breached a Vulnerability Disclosure Nonprofit by Chaining Two Zammad Zero-Days forkast.news
OpenAI Data Exposure
OpenAI apologizes to Australia after its AI agents breached government sites TechCrunch
GitHub Copilot Security Vulnerability
How we found 24 Android vulnerabilities using our open source AI security agent github.blog
Claude Security Vulnerability
Anthropic's Claude Opus 4.6 LLM has identified over 500 previously unknown, high-severity security vulnerabilities, including memory corruption and buffer overflow issues, in critical open-source libraries like Ghostscript, OpenSC, and CGIF. This demonstrates AI's emerging capability for sophisticated vulnerability discovery and code analysis, even for complex flaws requiring conceptual understanding of algorithms.
OpenAI Security Vulnerability
OpenAI’s Agent Hacked Australia’s Medicare Portal. It Found the Vulnerability Itself. forkast.news
EXCLUSIVE Data Exposure
EXCLUSIVE: OpenAI works to understand full scope of agent activity as user data leak emerges Reuters
Claude Security Breach
Three Open-Source AI Agents Ran 27+ Breaches for $25 a Target. 600,000+ Cards Followed. forkast.news
3 Cyber Threats That Defined the Summer of 2026
This installment of the Reporters' Notebook video series discusses the impact of AI agents breaching Hugging Face, Fairlife's ransomware attack, and Iranian-linked threat actors compromising a dozen US water systems. It was a busy summer.
Adobe Commerce Zero-day Vulnerability
Adobe on Monday released security patches to address a maximum-severity flaw impacting Adobe Commerce and Magento Open Source that has come under active exploitation in the wild. The vulnerability, now tracked as CVE-2026-75650 (CVSS score: 10.0), has been codenamed StyleSmuggler by Sansec, which discovered zero-day exploitation starting September 4, 2026. "This update resolves a critical
Amazon AWS Security Incident
Muse Mac App Security Flaw Allows Hackers to Exploit the AI Agent iPhone in Canada
Three-Person Team Uses Claude to Breach OpenAI's Core Codebase; $6,500 Bounty Triggers AI Security Alarm
Three-Person Team Uses Claude to Breach OpenAI's Core Codebase; $6,500 Bounty Triggers AI Security Alarm finance.biggo.com
AI Agent Breaches Spanish Organization, Modifies Personal Data
AI-driven cyberattacks used to be exotic. Soon, it'll be odd if threat actors aren't using agents to do all of their bidding.
Astra hidden vulnerability
The AI Security Problem Is Bigger Than the Hugging Face Breach HackerNoon
ChatGPT Remote Code Execution Vulnerability
AI agents, including Claude Sonnet 4.5, GPT-5, and Gemini 2.5 Pro, demonstrated high proficiency by solving 9 out of 10 lab challenges that simulated real-world web application vulnerabilities with minimal cost. These successes encompassed exploits like authentication bypass, IDOR, stored XSS, S3 bucket takeover, and AWS IMDS SSRF, highlighting AI's capability for multi-step reasoning and rapid pattern recognition.
ChatGPT Data Exposure
Autonomous AI agent hit Spanish firm with vulnerability scans before accessing files and data TechRadar
Spain reports first data breach involving autonomous AI agent
Spain reports first data breach involving autonomous AI agent Help Net Security
AI Data Breach
The Spanish Data Protection Agency (AEPD) was notified of an attack allegedly carried out with an AI agent powered by a known large language model (LLM). [...]
OpenAI Supply-Chain Compromise
The "major malicious attack" that targeted RubyGems in May 2026 was the work of a swarm of OpenAI agents, according to a new report published by researchers Spencer Kitts, Thomas Larsen, and Sydney Von Arx. On May 12, Maciej Mensfeld, senior product manager for software supply chain security at Mend.io, disclosed details of a coordinated cyber attack that targeted the package manager for the