#agentic AI
69 stories taggedagentic AI · page 4 of 5.
A Hidden Command in a GitHub Issue Can Silently Steal a Company's Private Code
Researchers found a flaw in GitHub's AI automation tool that lets an outsider read an organisation's private repositories by hiding plain-English instructions inside a public bug report.
AI Agents Can Be Tricked Into Sending Money. Zscaler Has the Data.
A new study shows that some expensive, enterprise-grade AI assistants fall for hidden instructions that most humans would ignore, and the real danger is far bigger than a fake three-dollar fee.
AI Agents Need Passports, Not Passwords
Companies are handing more decisions to autonomous AI agents, and the old rules about who gets access to what are breaking down. Here is what needs to change.
AI Is Making Decisions at Work. Most Companies Have No Rules for That.
Stephen Wilson, field CTO at HashiCorp, says businesses are giving AI tools real operational independence while still applying the loose oversight they used when AI only answered questions.
An AI Agent Broke Into a Server, Taught Itself to Adapt, and Left a Ransom Note
Security firm Sysdig says it has documented the first fully autonomous AI-driven ransomware attack, where a program called JadePuffer broke into a database, encrypted thousands of records, and demanded Bitcoin payment without a human criminal directing any step.
Hackers Are Hiding Instructions Inside Websites to Make AI Assistants Send Crypto Payments
Two newly discovered attack campaigns show how criminals can secretly hijack AI browsing agents by planting hidden commands in ordinary-looking web pages.
An AI Agent Ran a Ransomware Attack by Itself. Here's What That Means.
Criminals used an AI tool called Langflow to let a machine plan and carry out a multi-step ransomware intrusion without a human guiding every move, a shift that could make attacks faster and cheaper to run at scale.
Context Manipulation Attack 'BioShocking' Turns Agentic Browsers Into Credential Thieves
Researchers show how poisoned context fed to AI-driven browser agents causes them to drop safety guardrails and quietly exfiltrate stored credentials.
Cursor IDE's Sandbox Cracked by Prompt Injection — No User Interaction Required
Two logic flaws in Cursor's command execution sandbox let attackers escape the isolation layer and run code on the underlying OS. Patches landed in April. The researchers say Cursor isn't alone.
The Hidden Cost of Agentic AI in Security: Token Budgets Are Now a Defense Problem
Cybersecurity platforms are racing to embed agentic AI, but the economics of token consumption, AI credits, and deployment architecture may undercut the value before defenders see a return.
Prompt Injection in Git Repos Can Turn Claude Code Into a Reverse Shell Launcher
Malicious instructions buried in a repository's files can hijack Anthropic's Claude Code agent and open a backdoor on the developer's own machine, no obvious malware required.
Guardian Agents and the Identity Layer That Doesn't Exist Yet
Autonomous agents are inheriting human permissions at machine speed. The IAM stack wasn't built for this, and the governance gap is growing.
AI Agents Are Being Manipulated Through the Data They Trust
Hidden content injections and context poisoning are turning autonomous AI pipelines into attack surfaces. What defenders need to understand before deploying agents at scale.
The Patch Cycle Won't Survive Machine-Speed Adversaries
Defenders measured dwell time in days. Agentic attack pipelines are about to measure it in minutes.
Agentic AI Runs on Context. Feed It the Wrong Kind and Decisions Go Sideways Fast.
The core vulnerability in agentic AI systems isn't the model, it's the context window. Bad inputs, machine-speed outputs.