Stack layer / Threat pattern
MCPZoo Study: Scanners Call 96.89% of MCP Servers 'Risky' — But Under Half of Those Alerts Are Real
arXiv
Policy dependency / Stack layer
Cynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write Permissions
IT Security News
Stack layer / Contrast
Empirical Study: Microsoft's Early-2026 Rollout of Claude Code and GitHub Copilot CLI
arXiv / Hacker News
Stack layer / Update thread
Accelerated Mixing-Time Guarantees for Randomized Hamiltonian Monte Carlo
arXiv
Stack layer / Update thread
AgentLens: Open-Source Benchmark Scores the Whole Coding-Agent Trajectory, Not Just Pass/Fail
arXiv
Policy dependency / Threat pattern
Zhipu/Z.ai Founder Tang Jie's Internal Memo 'The Giant Wave Has Arrived': Frontier AI Must Stay Open — a Direct Rebuke of China's Rumored Curbs
Bloomberg
Stack layer
Aria: A General Code Agent + Verification Harness Proves All 4,257 Core Iris Lemmas Fully Automatically
arXiv
Stack layer / Threat pattern
Mako: A 'Self-Evolving Agentic OS' That Writes New Exploits Against Live Targets and Hot-Loads Them Into Itself
arXiv