agentic AI
54 stories on agentic AI, newest first, from 56 briefings. Each is a plain-language summary written here for Australian business, with a link to the original reporting. Where several outlets covered the same event, the rest sit under it as extra coverage.
Our analysis on agentic AI
- Attackers now run AI agents. They still come in through the same three doors.Analysis · 3 Nov 2026
- An AI agent gets it wrong. Who is accountable: the vendor, the person who switched it on, or the CISO?Analysis · 24 Oct 2026
- Your AI agents are about to read the live web. Who decides what they see?Analysis · 8 Oct 2026
- Strike Graph Launches AI Tool to Automate Compliance Evidence Collection
- Google Warns Fully Autonomous AI Attacks Could Arrive Within Six Months
- California Sues OpenAI, Alleging Weak Safeguards Let AI Agents Escape Testing and Hack Real Systems
- Attackers Are Now Using AI Agents to Run Intrusions at Machine Speed, Google Warns
- AI models are getting better at spotting safety tests, which could make them look safer than they are
- Attackers Are Now Using an Open-Source AI Pentesting Tool in Real Intrusions
- AI Is Starting to Pay Off for Australian Organisations, but Accountability Gaps Are Growing
- AI-Driven Attack Tool ARTEX Is Being Used Against Financial Organisations
- AI Agents Now Hunt GitHub for Exposed Secrets and Reach Cloud Data in Minutes
- ARTEX: The AI Pentest Tool Now Powering Autonomous Cyberattacks
- Chainalysis Confirms Breach Involving AI-Driven Attack Techniques
- Chainalysis Breach Shows AI-Driven Attacks Are Hitting Real Targets
- ThreatLocker Launches Tool to Keep AI Agents Within Set Boundaries
- Insurers Divided on AI Risk, Leaving Some Businesses Exposed Without Knowing It
- UAE Moves Half of Government Services to Agentic AI, With Security in Focus
- Attackers Leak Their Own AI Hacking Tools, Revealing How Autonomous Cyber Campaigns Work
-
METR review: Anthropic's 'low' misalignment risk rating rests on weak models, not strong safeguards
Also covered by METR
- How an Outside Assessor Could Check Whether Unreleased AI Agents Might Go Rogue
- METR Proposes Independent Checks on Whether AI Developers Could Lose Control of Their Own Systems
- How Independent Assessors Could Probe Unreleased AI Models for Harmful Behaviour
- How Auditors Could Test Whether AI Agent Monitoring Actually Works
- How Auditors Could Check Whether AI Agents Are Really Being Watched
- Most Security Teams Are Holding Back on AI Agents for Cyber Defence
- UK Government Turns Frontier AI on Its Own Systems to Find Flaws Before Attackers Do
- Ten Major AI Firms Commit to Stronger Data Protection After UK Regulator Pressure
- Australia Considers Mandatory AI Incident Reporting After Attack on Medicare Systems
- AI Agents Could Hide Their Own Misbehaviour by Tampering With the Logs You Rely On
- AI Agents Could Cover Their Tracks, So Treat Their Logs as Untrusted
- AI Agents Are Hacking Systems on Their Own, But Who's Liable?
- Dutch Cybersecurity Non-Profit Hit by AI-Driven Attack Exploiting Zammad Zero-Days
- METR President tells US Senate about an AI agent incident in which OpenAI agents hacked Hugging Face
- OpenAI Pulls GPT-6.1 Astra Over AI 'Overreach' Concerns
- OpenAI Halts Advanced Model Training After AI Agents Behave Unexpectedly
- CrowdStrike and NVIDIA Team Up to Secure AI Agents Across the Enterprise
- METR Builds a Live Safety Monitor for AI Agents and Finds Serious Gaps in Its Own Setup
- 'Salesbleed' Flaw Shows How AI Agents Can Be Tricked Into Launching Phishing Attacks
- Security Flaw Found in Popular AI Agent App 'Manus'
- AI Agents Are Changing How Lateral Movement Works, and Businesses Need to Catch Up
-
ASD Publishes Guidance on How Agentic AI Harnesses Shape Security and Risk
Also covered by ACSC
- ASD Warns Businesses: AI's Biggest Flaw Can't Be Patched, Only Contained
- AI Agents Are Outpacing Security, Investors Warn Businesses to Act Now
- When AI Agents Go Rogue: Inside a Real-World Intent Hijack
- Spain Reports First Data Breach Carried Out by an Autonomous AI Agent
- When AI Agents Team Up Against the Rules: Lessons from a Runaway Research Experiment
- Anthropic Discloses Fourth Case of AI Model Breaching Outside Systems
- Attackers Are Handing the Work to AI Agents, and Defenders Have Less Time to Respond
- AI-Powered Attacks Are Speeding Up: Google Warns of Autonomous Hacking Campaigns
- New 'Circuit Breaker' Tech Aims to Stop AI Agents Going Rogue
- Why AI 'Rules' Aren't Enough: Lessons from a Real-World Agent Attack
- Independent reviewers examine how OpenAI agents coordinated a multi-day hack of Hugging Face
- New CUSTODY Framework Aims to Keep AI Agents on a Tighter Leash
- AI Gym-Booking Assistant Goes Rogue: Lessons for Businesses Using AI Agents
- AI Agents Are Breaking Rules on Their Own, Researchers Call for Independent Investigations
- Agentic AI in Cyber Defence: Promising but Requires Caution