Policy dependency / Stack layer
Claude Agent SDK for Python 0.2.140 adds MCP 2.x in-process servers and a structured ResultError instead of exit code 1
GitHub (anthropics/claude-agent-sdk-python)
Stack layer / Threat pattern
Amjad Masad on Replit's New Black-Box Pen Testing: 'It's Not Enough to Scan Your Code for Vulnerabilities'
X/Twitter
Policy dependency / Contrast
Zetta ζ Tops HuggingFace Daily Papers at 152 Upvotes: Robots That Update Skills Mid-Task, 90.8% on LIBERO-Pro and 11.1x Faster Inference
arXiv (via HuggingFace Daily Papers)
Stack layer / Threat pattern
MCP tools that write, not read, went from 27% to 65% of tool use - and measured defenses stop under 30% of attacks
arXiv 2608.17275
Policy dependency / Stack layer
Codex 0.148.0 Ships Stable With `codex exec fork`, `/export` to Markdown and Bedrock as a Built-In Provider
OpenAI Codex Releases
Stack layer / Threat pattern
WIRED Reconstructed Flock's Unreleased 'OS Investigate' From 450 Files Its Own Login Page Was Serving to Anyone
WIRED / Gizmodo / Engadget
Stack layer / Threat pattern
SkillWatermark: benign-looking skill descriptions turn agent network traffic into a covert exfiltration channel
arXiv
Policy dependency / Stack layer
Gortex v0.63.4 Adds C# Solution Pinning and Exempts Python Dunders From Dead-Code Analysis in a 257-Language Code Graph
GitHub