The extension amassed over 300,000 installs and a 4.6 rating before Google removed it for stealing data.
Tag: AI Security
New ‘Ghostjacking’ Attack Lets Hackers Hijack AI Agents to Run Their Code on Developer Machines
A new AI-agent attack technique called “Ghostjacking,” can trick coding agents into running attacker-controlled commands, changing cloud settings,…
Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
A malicious tool server connected to an AI coding assistant can quietly walk off with SSH keys, environment secrets, source code, and customer data…
GhostJacking Attacks Let Hackers Hijack AI Agents and Steal Cloud Credentials
Security researchers have disclosed “GhostJacking,” a new class of attacks that exploits trusted observability and security platforms to manipulate AI…
Senior Police Detective Probed Over AI Use
Senior police detective in Derbyshire investigated by IOPC over alleged gross misconduct related to AI use
Consulting Giant EY Sets Up Unit To Monitor AI Costs
Consulting giant creates ‘AI value realisation’ office, builds cost-cutting ‘AI router’, as firms seek to manage spiralling expenses
Nvidia Works With Financial Giants On $500bn AI Funding Package
Nvidia reportedly finalising deal with world’s largest financial firms on major package to help fund AI data centre boom
1Password Finds AI Security Patches Fail More Than Half the Time
A 1Password study found AI-generated security patches failed to fully fix vulnerabilities in more than half of tested cases.
Anthropic to Add Invisible Watermarks to All Claude AI Outputs
Anthropic has announced plans to add invisible watermarks and signed metadata to content created by Claude AI. The move follows the company’s decision to…
An AI tool found 84 flaws in 5G network software and 23 of them still have no fix
Researchers at Nanyang Technological University turned a set of AI agents loose on the software that runs 4G and 5G phone networks, and the agents came…
Gym Booking Task Turns Into Real-World AI Cyberattack
An AI agent hacked a gym booking system while trying to help a user, booking early and removing another person from the waitlist. An Australian man asked…
North Korean spies are running local LLMs to cause AI mischief
Kimsuky’s phishing attacks get an AI boost
DEF CON 34: 10 Vulnerabilities Put Local AI at Risk
DEF CON 34 research revealed 10 vulnerabilities in llama.cpp, exposing critical memory-safety flaws.
Gym rat asks AI agent to book him a class, it hacks a waitlist API to bump him up the list
What wouldst thou ask of the monkey’s paw?
⚡ Weekly Recap: AI Goes Rogue, Metabase 0-Day, MCP Supply-Chain Attacks, and Router Backdoors
A lot of security problems still begin with someone doing a completely normal thing. Cloning a repo. Answering a call. Leaving a box exposed. Trusting the…
Researchers Uncover RovoBlast Vulnerability in Atlassian AI Assistant
Atlassian fixed a flaw letting one crafted link make its Rovo AI assistant exfiltrate company data
China’s New Challenge: Fake AI Videos During Natural Disasters
As China grapples with intensified storms and flooding over recent months, authorities face an unexpected secondary crisis: a surge of AI-generated fake…
Margarita Howard’s HX5 Operationalizes CMMC Compliance Before AI Rules Arrive
Margarita Howard has spent two decades running a company in a government contracting market where the rules rarely hold still. HX5, the defense and…
Stealthium Targets Security Blind Spots in AI Accelerators and Neo-Clouds
The startup analyzes subtle telemetry signals to detect attacks that traditional security tools cannot see inside accelerator-powered AI infrastructure.
Kimsuky Builds Offline AI Stack to Boost Phishing and Automate Malware Development
North Korea’s state hackers are no longer content to type prompts into public chatbots. One of the country’s main espionage groups has begun running…