AI Agents
One Stolen Key, 181 Nodes: Tailscale's Three Controls
Tailscale found no vulnerability in the Hugging Face intrusion, yet one reusable CI key enrolled 181 nodes. The three controls that make that key inert.
23 days ago
Ai Security
All articles about Ai Security
More articles
Claude
Claude's AES Attack Took a Week to Find, a Month to Verify
Anthropic's Claude Mythos Preview found a 7-round AES attack in one week. Two researchers needed nearly a month to verify it. Why review is the real cost.
26 days ago
OpenAI
Hugging Face Asks OpenAI for Rogue Agent Logs and $100M
Clem Delangue asked OpenAI to release the rogue agent traces and commit $100M. The part that matters for defenders: hosted safety filters blocked the forensics.
28 days ago
AI Agents
Alibaba's Claude Code Ban Is Now a Supply-Chain Test
Alibaba’s Claude Code ban turns a disputed backdoor warning into a practical vendor-risk checklist for AI coding teams.
about 1 month ago
AI Agents
How to Audit AI Agent Skills Before They Burn Your Stack
One in four AI agent skills carries a security flaw. NVIDIA open-sourced SkillSpector to scan them — here's a practical pre-deploy audit playbook.
2 months ago
AI Agents
Claude Code 2.1.166: The Multi-Agent Trust Boundary Moved
A one-line change in Claude Code 2.1.166 strips borrowed authority from relayed agent messages. Here's why the multi-agent trust boundary just moved.
3 months ago
AI Agents
Security Harnesses, Not Vibes: Vercel deepsec
Vercel deepsec shows why AI-coded apps need repeatable security harnesses, second-agent revalidation, and controlled merge gates.
4 months ago
AI Agents
Running Codex Safely: OpenAI’s Security Playbook
OpenAI’s Codex safety post turns coding-agent adoption into a control system: sandboxing, approvals, network policy, credentials, and telemetry.
4 months ago
Claude
Claude Code Security: AI Vulnerability Scanning Guide
How Anthropic's new security tool finds bugs that static analysis misses — and how to use it effectively.
6 months ago
MCP
AI Ecosystem Update Week 4/2026: ChatGPT Tests Ads, Claude Cowork Goes Live, and Critical MCP Security Flaws
Week 4/2026 brings major AI updates: OpenAI tests ChatGPT ads for 800M users, Claude Cowork automates desktop tasks, Google connects Gemini to Gmail and Photos – and critical MCP security flaws reveal new risks for AI agents.
7 months ago
MCP
Context Engineering: How to Build Reliable LLM Systems by Designing the Context
Context engineering is the discipline of curating, structuring, and defending everything that reaches the LLM at inference time. This comprehensive guide covers 2026 best practices for building reliable AI systems.
8 months ago