7 articles with this tag
MCP Security Vulnerabilities 2026: MCP Is the New NPM
MCP (Model Context Protocol) security vulnerabilities in 2026: how supply-chain risk and indirect prompt injection turned MCP into the new npm.
When Your Agent Becomes the Exploit: ASI05 & ASI06 — The Twin Threats That Turn AI Autonomy Against You
A deep dive into OWASP Agentic ASI05 and ASI06: the Claude Code CVEs, the Summer Yue incident, and how code execution chains with memory poisoning.
The OpenClaw Meltdown: 9 CVEs, 2,200 Malicious Skills, and the Most Comprehensive Real-World Test of the OWASP Agentic Top 10
In 5 weeks, OpenClaw triggered 8 of 10 OWASP Agentic vulnerability classes. This is the forensic dissection every engineer building AI agents needs to read.
The New Security Bible: Why Every Engineer Building AI Agents Needs the OWASP Agentic Top 10
The OWASP Agentic Top 10 is the first security framework for autonomous AI agents. 10 risks, real incidents, and the attack chains that connect them.
The Compiler vs The Browser: Two Armies of AI Agents Walk Into a Codebase
Anthropic's 16 Claude agents built a C compiler. Cursor's hundreds built a browser. A deep teardown of two blueprints for autonomous software development.
Beyond the Autocomplete: Why the MCP Revolution is the End of 'Copilot' as We Know It
The Agentic IDE Era has arrived. From Xcode 26.3 to GitHub Agent HQ, we're moving from passive suggestions to autonomous engineering. Here's the stack.
The Agentic CLI Takeover: Why Your Terminal is the New IDE Frontier
Autonomous AI agents are taking over the terminal. The architecture behind agentic CLIs, the security risks, and why your shell history is now an asset.