What's new
Will AI Replace Security Researchers? What Changes Now
Will AI replace security researchers? Mythos-class models find vulnerabilities faster, but verification, triage, and initial access still need humans. Read More
AI-Generated Code Security: What the Testing Actually Shows
AI writes half of all code and fails security tests 44% of the time. See the failure profile, why... Read More
AI-to-AI Communication Risks: What MCP and A2A Actually Expose
AI-to-AI communication already runs on MCP and A2A, and neither mandates an audit trail. See how each fails, and... Read More
Attacks Against AI Systems: The Three Lists That Organise Them
Attacks against AI target the system itself, not your inbox. See the three OWASP lists covering the model, agent,... Read More
Using AI to Defend Against AI Attacks: What Actually Works
AI now runs inside live malware. See where AI defence genuinely helps, where egress policy beats it, and a... Read More
How to Implement AI Agents Securely: Permissions Over Detection
Implement AI agents securely by scoping tools, isolating identity, and keeping authorization outside the model. Permissions decide the damage,... Read More