Policy dependency / Stack layer
Cynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write Permissions
IT Security News
Stack layer / Threat pattern
MCPZoo Study: Scanners Call 96.89% of MCP Servers 'Risky' — But Under Half of Those Alerts Are Real
arXiv
Stack layer / Threat pattern
'Ghost Commit' Disclosure: PNG-Hidden Prompt Injection Makes Cursor and Anti-Gravity Exfiltrate .env Secrets
awesome-ai-agent-attacks timeline
Stack layer / Update thread
QwenPaw 2.0 Ships a Ground-Up 'Agent OS' Rewrite on AgentScope 2.0
GitHub
Same source domain / Semantic neighbor
Give long-horizon agents a message-gateway plus per-task sandboxed filesystem, as ByteDance DeerFlow does out of the box
GitHub
Policy dependency / Threat pattern
Compliance SaaS Pivots to Governing Agents: Vanta's AI Agent Reaches GA in July; Drata Declares 'AI Agent Governance' a New Category
Drata (corroborated by Vanta/SiliconANGLE)
Stack layer / Update thread
llama.cpp Merges Native Hy3 Support (PR #25395) — Tencent's 295B MoE Now Runs Locally via 1-Bit/4-Bit GGUF
llama.cpp (GitHub PR #25395) / Hugging Face
Stack layer / Update thread
Show HN: Jacquard — A Programming Language for AI-Written, Human-Reviewed Code
GitHub / Hacker News