Policy dependency / Stack layer
Codenotary ships AgentMon 3 for agent runtime policy and compliance logging
AI Agent Store
Stack layer / Threat pattern
Microsoft Agent Framework python-1.11.0 adds Progressive MCP Disclosure and GA Skills API
GitHub (Microsoft Agent Framework)
Stack layer / Threat pattern
Tip: Update Headless Claude Code to v2.1.207 — Managed-Settings Consent Was Silently Auto-Recorded
Claude Code Changelog
Stack layer / Threat pattern
GitHub Ships CodeQL 2.26.0 With AI Prompt-Injection Detection for JavaScript/TypeScript
GitHub (CodeQL release notes)
Stack layer / Threat pattern
Varonis discloses 'Rogue Agent' — a Dialogflow CX flaw letting one permission poison a shared agent runtime
NxCode
Stack layer / Threat pattern
Pick your agent sandbox primitive by threat model: Firecracker microVM vs gVisor vs V8 isolate
Northflank
Stack layer / Threat pattern
Mitigating Taint-Style MCP Server Vulnerabilities Without Touching Server Code (SPELLSMITH)
arXiv
Stack layer / Contrast
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)