Policy dependency / Stack layer
Cynative Ships an Open-Source Deep-Research Security Agent With Default-Deny Write Permissions
IT Security News
Policy dependency / Stack layer
Codenotary ships AgentMon 3 for agent runtime policy and compliance logging
AI Agent Store
Policy dependency / Stack layer
FT: OpenAI and Google Sold AI Services to Pentagon-Blacklisted Chinese Firms via Singapore Units
Financial Times (via Yahoo Finance)
Stack layer / Threat pattern
BackendForge: Best Coding Agent (GPT-5.5) Deploys Correct Backends Only 28.6% of the Time Under a Strict Oracle
arXiv
Stack layer / Threat pattern
Claude Code's July 10 Update Hardens the Agent Loop Against Forged Approvals: Transcript-Tamper Blocking + 'No Human Input Occurred' Notices
Releasebot (Anthropic Claude Code changelog, corroborated by code.claude.com/docs/whats-new)
Policy dependency / Stack layer
Defend against MCP tool poisoning by pinning versions and alerting on any tool-description change between releases
Practical DevSecOps
Stack layer / Threat pattern
SLBench Finds Up to 70% Unsafe Execution When Codex and Claude Code Follow Logical Relations in Skill Files
arXiv
Policy dependency / Stack layer
HHS Is Using ChatGPT (AERO) to Audit $2.1T in Federal Health Spending — With No Published Error Rate
Tech Times