Advertisement
How Agentjacking Exploits AI Coding Agents via Fake Bug Reports
Researchers demonstrate 'Agentjacking,' a technique using indirect prompt injection to hijack AI coding agents through malicious GitHub bug reports.
Anthropic Claude Fable 5 Restored After U.S. Export Control Lift
Anthropic restores global access to Claude Fable 5 following the lifting of U.S. export controls linked to jailbreaking vulnerabilities and security concerns.
Phantom Squatting: How Attackers Weaponize AI-Hallucinated Domains
Security researchers have identified 'Phantom Squatting,' a technique where attackers register non-existent domains hallucinated by AI for phishing.
Declining Confidence in Autonomous Penetration Testing: 2024 Analysis
Security leaders are re-evaluating autonomous penetration testing due to accuracy concerns, shifting focus toward human-led automated security validation.
Autonomous Agentic AI Adversaries: Managing Machine-Speed Cyber Threats
The transition to agentic AI adversaries marks the end of human-speed threats. Learn how autonomous agents automate exploit discovery and execution at scale.
Agentic AI Cyber Warfare: Risks of Autonomous Offensive Operations
Analyze the shift from human-led to autonomous agentic AI cyber attacks, exploring detection challenges and strategies for mitigating offensive AI agents.
Anthropic Disables Fable 5 and Mythos 5 for Export Control Compliance
Anthropic has taken its Fable 5 and Mythos 5 AI models offline following a Trump administration directive aimed at restricting foreign access to advanced AI.
US Bans Anthropic Fable 5 and Mythos 5 Over National Security Risks
Anthropic suspends Fable 5 and Mythos 5 AI models following a US government order citing national security risks regarding access by foreign nationals.
Claude Fable 5: Anthropic Unveils New High-Performance AI Model
Anthropic releases Claude Fable 5, a limited-time high-performance AI model based on the Mythos architecture, targeting advanced reasoning and efficiency.
Anthropic Mythos Preview: Advancing AI Offensive Security Performance
XBOW evaluates Anthropic's Mythos Preview model, revealing high efficacy in automated vulnerability discovery, reverse engineering, and exploit development.
AI Code Generation Security Risks: Managing Vibe Coding Governance
Learn how to manage AI code generation security risks and implement governance for vibe coding practices in the software development lifecycle.
Unpatched Comodo Antivirus Flaw and Anthropic AI Threat Mapping
Researchers reveal an unpatched privilege escalation flaw in Comodo Antivirus and a new taxonomy for AI-driven cyber threats by Anthropic and the UK AISI.