Unbounded consumption is an issue that OWASP currently ranks sixth in its Top 10 for LLM Applications, and it could be an extremely costly one.
Security teams investigating possible AI-related security events need guardrail intervention data alongside their existing security telemetry. When a guardrail identifies or blocks a prompt injection attempt or redacts sensitive data, that intervention carries additional investigative value comparable to a failed sign-in or a network intrusion alert. AWS Bedrock publishes this telemetry to AWS CloudWatch metrics […]
A browser. A plugin. A package. A login screen. Normal stuff. That is basically the problem this week. The trouble keeps showing up inside things people already trust: code that takes a bad turn, old payloads coming back, exposed systems, weak checks, fake fixes, and attack paths that look almost too easy. Even the research side is getting messy, with more findings, more automation, and not
Google’s artificial intelligence model Gemini accessed computer systems belonging to three real companies without authorization during a cybersecurity test in May — the latest in a string of similar incidents.
As AI opens new paths to company data while making familiar attacks faster and cheaper, SMBs need protection designed around the time and expertise available to operate it
AI agents are becoming the new attack surface, exposed to poisoned skills, prompt injection, jailbreaks and attacks through connected tools. I read the AI security research published in a single month, February 2026, and when you put it all together, it’s not a list of curiosities. It’s a field guide to a new attack surface. […]
Google Gemini escaped a cyber test environment, reached three real companies, and exposed why AI security tests need strict isolation. Google has confirmed that one of its Gemini models broke into the systems of three real companies during a cybersecurity test in May. The incident is the first publicly known case in which a Google […]
Google's Gemini model has become the latest artificial intelligence (AI) system to access the internet and break into other companies during a cybersecurity evaluation. The development was first reported by The Wall Street Journal. The incidents occurred in May 2026 as part of a test run conducted by Israeli company Irregular. The evaluation partner was also involved in similar hacks disclosed
Analysis of how default configurations in AWS AgentCore Harness allow prompt injection to exfiltrate credentials, and key steps to secure your agents. The post A Vault with a Heap-View: The Uncomfortable Space Between AgentCore Harness and Identity appeared first on Unit 42.
A financially motivated threat actor has been linked to the development and distribution of a JavaScript (JS)-based information stealer known as PhantomRaven via the npm package registry. "The developer likely wrote the malware using a large language model (LLM), an assessment made with high confidence based on verbose comments, placeholder code, and statistical token-analysis patterns,"
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.
Cybersecurity researchers have flagged a new Android malware called RatHat that's assessed to be operated by China-based threat actors and features an artificial intelligence (AI)-powered system to navigate and control compromised devices. "Distributed primarily via targeted smishing (SMS/text phishing) and malvertising campaigns leading to deceptive third-party download portals, RatHat uses
OpenAI has presented new examples of what they call "AI model misalignment" from the past six months, including unauthorized file uploads, following self-generated instructions, hiding mistakes, and leveraging exposed API keys. [...]
Attackers now weaponize new vulnerabilities in about five days (Mandiant, part of Google Cloud). The median organization takes 43 days to patch one (Verizon DBIR 2026). A new free guide explains how autonomous AI agents are closing that gap, and what security leaders must demand before pointing one at production. TL;DR Exploitation is now the front door. It starts 31% of breaches (Verizon DBIR
New research from Irregular shows AI agents can retrain and redeploy their own underlying models during routine maintenance tasks. The post AI Agents Can Retrain Own Models Mid-Task, Leaking Secrets and Erasing Refusals appeared first on SecurityWeek.
CISOs are not waiting for AI to prove its cybersecurity value before investing in the technology. Is it the right move?
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). [...]
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). [...]
Spanish regulators say an AI agent chained together a successful login, vulnerability discovery, and access to personal data in a potential milestone for autonomous cyberattacks. The post First Agentic AI Data Breach Reported to Spanish Regulator appeared first on SecurityWeek.
The company provides a standard for AI systems, testing them against risks such as jailbreaks, prompt injections, and unauthorized actions. The post AIUC Raises $40 Million to Certify Enterprise AI Agents appeared first on SecurityWeek.
The cybersecurity startup is building a proprietary foundation model and plans to accelerate global expansion. The post Exein Secures $270M at $1.7B Valuation for Physical AI Security appeared first on SecurityWeek.
The incident occurred in May, when RubyGems maintainers suspended new account registrations due to what appeared like malicious activity. The post OpenAI Investigates Report Linking AI Agents to RubyGems Attack appeared first on SecurityWeek.
With artificial intelligence (AI) shrinking the window between vulnerability discovery and exploitation and lowering the barrier to entry for bad actors, new findings from Sysdig show that skilled human operators can move just as swiftly after gaining initial access. In one instance highlighted by the cloud security company, the threat actor pivoted from a vulnerable Marimo notebook to an SSH
AI keeps showing up in the wrong places. Attackers are using it to speed up exploits, test defenses, and automate more of the job. Some models are also crossing lines on their own. That is not a great combination. The rest of the week is more familiar: old bugs still working, fresh exploit chains, exposed systems, weak defaults, and simple paths that should have been harder to abuse. A few of
Security leaders are struggling to modernize cyber hygiene and prevent over-privileged agents from causing unintended harm. The post CISOs Race to Control AI Agents Without Destroying Their Value appeared first on SecurityWeek.
AI is becoming an operational force for cybercrime, surveillance, propaganda, fraud and weapons development, lowering the cost and scale of attacks. Artificial intelligence (AI) is becoming more than a tool for people who want to do something malicious. It is increasingly becoming part of the operational machinery itself. That is the main message emerging from […]
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
Bulletin ID: 2026-111-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 09/11/2026 12:00 PM PDT Description: Kiro IDE is an agentic development environment that makes it easy for developers to ship real engineering work with the help of AI agents. We identified CVE-2026-89332, where the Kiro agent could modify a workspace's settings file in an untrusted workspace in Kiro IDE. A specially crafted repository could use this to point the Kiro Powers registry URL, which K…
The Dubai-based threat detection startup uses artificial intelligence tools to scan billions of IP addresses to find exposed assets, leaked data, and zero-day vulnerabilities.
I identified an attacker using a semi-autonomous coding agent to run an offensive operation: finding poorly secured LLM resale gateways, acquiring API access through ordinary web flaws and account farming, validating the resulting inference capacity, and aggregating it behind a single gateway of their own.
