Storyline
AI Agent Security Tools and Red Teaming
Microsoft and Google are releasing open-source security tools designed to test and secure AI agents during development as vulnerabilities in AI-generated code become a growing concern. Microsoft's RAMPART and Clarity tools enable developers to identify security flaws in agentic AI applications, while Google's CodeMender provides similar code security capabilities in competition with Anthropic's offerings.
This is a long-running storyline that has developed over 9 days. The homepage highlights its most recent activity, so the outlet count there reflects the latest wave. The totals above cover the full run.
MicrosoftGoogleAI agentsRed teamingCode security
2026-05-27
- Casa Launches Four Security Features to Combat Rising Social Engineering Attacks on Bitcoin Holders
- AI-Assisted Exploit Development Outpaces Scanner Detection
- Aztec Labs acquires ZKPassport, pledges to keep privacy protocol and iOS mobile app open-source
- Researchers find all big-name bots bomb EU compliance tests
- Huawei's New Benchmark Gives AI Agents Months of Your Life—Then Watches Them Fail
- Show HN: I made an emergency page for my family. You should too
- US law enforcement warns of "anti-tech extremism" as AI hatred grows
- DeFi isn't safe anymore because AI is becoming 'superhuman' at hacking, security chief warns
- Explainer: Edge AI
2026-05-26
- For Enterprises, Security Remains Agentic AI's Biggest Challenge
- Microsoft Defender can now automatically isolate hacked endpoints
- Spotify says its AI remix tool protects artists from unregulated ‘slop’
- New AI DDoS Attacks Are Smarter. Learn How to Fight Back in This Webinar
- The SaaS-pocalypse can wait, Salesforce still has customers where it wants them
- US Law Enforcement Warns of ‘Anti-Tech Extremism’ as AI Hatred Grows
- AI agents must be treated as untrusted systems: Researchers
2026-05-25
- Famed iPhone, Sony Hacker Says AI Coding Agents Are a Disaster Waiting to Happen
- Exit IP VPN servers mitigation rollout
- Perplexity Built a Tool That Checks Your Computer for Infected Software—Without Setting Off the Infection
- Anthropic’s restricted Claude Mythos model may be coming to Claude Code
- AI guardrails stripped from Meta and Google models in minutes
- Anthropic to release Mythos-class models to the public