Policy dependency / Stack layer
Reason Less, Verify More: Deterministic Gates Catch a Silent Policy-Violation Failure in Tool-Using Agents
arXiv
Stack layer / Threat pattern
Ghostcommit hides prompt injection in PNG files to make AI coding agents exfiltrate repo secrets
SecNews
Stack layer / Contrast
Mira Murati's Thinking Machines Makes the Technical Case for User-Owned Model Weights
MarkTechPost
Policy dependency / Stack layer
Codenotary ships AgentMon 3 for agent runtime policy and compliance logging
AI Agent Store
Policy dependency / Stack layer
First Recon AI ships AI Security Runtime GA — inline policy enforcement on every agent-to-agent and agent-to-tool call
Business Wire
Stack layer / Contrast
Long-Horizon-Terminal-Bench: Best Frontier Agent Clears Just 15% of Real Terminal Tasks, Mean 4.3%
arXiv (Tencent Hunyuan) / HuggingFace Daily Papers
Threat pattern / Follow-up thread
VEXAIoT: arXiv paper demonstrates autonomous IoT vulnerability exploitation using AI agents
arXiv
Stack layer / Update thread
Goose v1.40.0 Adds a Local 'goose review' Command and Peek Mode for Async Background Tasks
GitHub