Collaborate Disseminate
Researchers uncovered two campaigns embedding indirect prompt injections in malicious websites to exploit autonomous AI agents browsing the web.
The post Prompt Injection Attacks Trick AI Agents Into Making Crypto Payments appeared first on SecurityWeek.
Continue reading Prompt Injection Attacks Trick AI Agents Into Making Crypto Payments
Attack demonstrates how LLM agents can combine known exploitation techniques with real-time reasoning to automate complex, multi-stage intrusions.
The post Agentic AI Used to Conduct Ransomware Attack via Langflow appeared first on SecurityWeek.
Continue reading Agentic AI Used to Conduct Ransomware Attack via Langflow
Medical technology giant Medtronic is notifying more than 3.8 million individuals that their personal and medical information was compromised in a recent data breach. The incident occurred in April 2026, when the infamous extortion group ShinyHunters a… Continue reading Medtronic Data Breach Impacts 3.8 Million People
Prosecutors say 19-year-old Peter Stokes was a member of Scattered Spider, the hacking group linked to more than 100 network intrusions and over $100 million in ransom payments.
The post Alleged Scattered Spider Hacker Extradited to US appeared first o… Continue reading Alleged Scattered Spider Hacker Extradited to US
NetNut rented access to millions of compromised devices, allowing cybercriminals and nation-state actors to mask their identities during attacks.
The post Google, FBI Disrupt NetNut Residential Proxy Network Powered by Millions of Devices appeared firs… Continue reading Google, FBI Disrupt NetNut Residential Proxy Network Powered by Millions of Devices
The DuneSlide vulnerabilities enable zero-click prompt injection attacks that escape Cursor’s sandbox and execute arbitrary code on the underlying operating system.
The post Critical Cursor AI Code Editor Flaws Could Lead to OS-Level Remote Code Execut… Continue reading Critical Cursor AI Code Editor Flaws Could Lead to OS-Level Remote Code Execution
Hackers are targeting NetScaler appliances using public PoC code to retrieve arbitrary memory content in the HTTP response.
The post New CitrixBleed Vulnerability Exploited Immediately After Public Disclosure appeared first on SecurityWeek.
Continue reading New CitrixBleed Vulnerability Exploited Immediately After Public Disclosure
Researchers say credentials harvested from hundreds of thousands of FortiGate firewalls are being used to facilitate ransomware attacks by the INC and Lynx operations.
The post FortiBleed Campaign Linked to INC, Lynx Ransomware Attacks appeared first o… Continue reading FortiBleed Campaign Linked to INC, Lynx Ransomware Attacks
A PoC exploit has been available since public disclosure, and the first exploitation attempts were observed last week.
The post Cisco Confirms In-the-Wild Exploitation of Unified CM Vulnerability appeared first on SecurityWeek.
Continue reading Cisco Confirms In-the-Wild Exploitation of Unified CM Vulnerability
Researchers show how context manipulation can cause agentic browsers to abandon safety guardrails and exfiltrate sensitive credentials.
The post ‘BioShocking’ Attack Tricks AI Browsers Into Stealing Credentials appeared first on SecurityWeek.
Continue reading ‘BioShocking’ Attack Tricks AI Browsers Into Stealing Credentials