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
GitLost: prompt injection in GitHub Agentic Workflows leaks private repos with zero credentials (CVE-2026-44246)
explainX (reporting Noma Security research)
Stack layer / Contrast
Empirical Study: Microsoft's Early-2026 Rollout of Claude Code and GitHub Copilot CLI
arXiv / Hacker News
Policy dependency / Update thread
NetInjectBench: Naive Network-Ops Agents Take Unsafe Actions 82.5% of the Time Under Prompt Injection
arXiv
Threat pattern
GitHub Ships 'Agentic Autofix' in Public Preview — Copilot Now Explores, Fixes, and Re-Runs CodeQL Before Opening a PR
GitHub
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
Policy dependency
Simon Willison Finds a Cache-Friendly uvx Recipe for GitHub Actions: Pin UV_EXCLUDE_NEWER Into the Cache Key
Simon Willison
Stack layer / Threat pattern
Mako: A 'Self-Evolving Agentic OS' That Writes New Exploits Against Live Targets and Hot-Loads Them Into Itself
arXiv