Stack layer / Threat pattern
OpenClaw ships broad July 6 platform update: GPT-5.6 support, external harness attach, hardened provider I/O
Releasebot
Stack layer / Threat pattern
TRACE Watermarks Agent Trajectories Against Adversaries Who Control the Logs
arXiv
Stack layer / Threat pattern
NSA issues official MCP hardening guidance after Amazon Q auto-execution CVEs (CVSS 8.5) enable AWS credential theft
Wiz
Policy dependency / Stack layer
IAPS warns on Kimi Claw: security and governance risks of Chinese-hosted 'always-on' AI agents
IAPS
Threat pattern / Follow-up thread
ClawHavoc campaign plants 300+ malicious skills on a single marketplace to run infostealers
Unit 42 (Palo Alto Networks)
Stack layer / Contrast
browser-use Ships 'Browser Harness' — Agents Edit Their Own Browser Helpers Mid-Task Instead of Failing
GitHub
Stack layer / Follow-up thread
ThursdAI, July 9: OpenAI Claims Sol Autonomously Post-Trained Luna
ThursdAI (Alex Volkov)
Policy dependency / Stack layer
Kastra Launches Policy Enforcement for Claude Code, Cursor, and Codex
Hacker News