References
How to build an AI scientist: first peer-reviewed paper spills the secretsMachines of Loving Grace
- AI Scientist in Practice: Reproducing and Evaluating Autonomous Scientific Discovery
SciAgents: Automating Scientific Discovery Through Bioinspired Multi-Agent Intelligent Graph Reasoning
A multi-agent system for automating scientific discovery- How an obscure website became a force in America's election information machine
Anthropic Leaks Claude Code Source Code
Anthropic Quietly Fixed Serious Path Traversal and Injection Flaws in Its MCP Git Server
The Hidden Backdoor in Claude Coding Assistant
Inside the ‘clawdhub’ Malicious Campaign
Researchers Uncover 30 Flaws in AI-Powered IDEs — IDEsaster
Weaponizing AI Coding Agents for Malware: The Nx Incident- The State of Secrets Sprawl 2026
North Korean fake job interview led to $6.3B Binance heist
How We Built Safety Into Muse (Meta)- Leveraging LLM Agents for Automated Video Game Testing
How we contain Claude across products
Security incident disclosure — July 2026
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
Inside the LiteLLM 1.107.0 supply chain compromise: Credential theft through Python startup hooks | Microsoft Security Blog