• Agent Threat Rules: Open detection rule format for AI agent security threats
• Known vulnerabilities behind most application security incidents
• Infosecurity Europe: NCSC Urges Immediate Action to Boost Resilience as Uncertainty Persists
• Infosecurity Europe: Cybersecurity Teams Which Don’t Leverage AI are "Doomed to Fail"
• Infosecurity Europe: Bayer Reinvents Security Awareness Training to Counter AI Threats
• Meta adds stricter guardrails for teen feeds
• 64,000 accounts exposed in breach of GTA V cheat service Atlas Menu
• Codex knowledge work expands into research, reports, and spreadsheets
• Google fixes actively exploited Android vulnerability (CVE-2025-48595)
• Threat Actor Uses AI to Build EDR Evasion Tools
• Infosecurity Europe: UK Firms Prioritize AI Threat Preparedness as Cyber Risks Evolve
• Attackers Hijack Red Hat npm Scope to Steal Cloud Secrets
• Infosecurity Europe: Business Leaders Lack Understanding of Threat Intelligence, Study Warns
• Critical Flowise Flaw Gives Attackers Full Server Control
• Infosecurity Europe: Tabletop Exercise to Test How CISOs Respond to Major Supermarket Cyber-Attack
• Infosecurity Europe: AI SOCs Will Still Need SOC Analysts, Security Vendors Say
• FSB Group Gamaredon Hides Worm in Windows Data Streams
• Attackers Abuse Shared Content for ChatGPT Phishing Campaign
• Palo Alto Warns High-Severity Bug Is Being Actively Exploited
• Infosecurity Europe: OWASP Forms New Agentic Research Council
• Silent Ransom Group Uses In-Person IT Impersonation to Breach Systems

AI agents run inside coding assistants, MCP servers, and multi-agent frameworks, and the access that makes them useful also opens paths to prompt injection, tool poisoning, and credential theft. Public CVE feeds carry agent-execution flaws that reach production faster than the tooling built to catch them. Agent Threat Rules, or ATR, is an open detection format aimed at this category of attack. ATR rules are YAML documents that conform to a versioned schema. Each one …