AI Security
Recent Articles
Safety & Ethics
What does the left-pad incident teach us about modern supply chain attacks?
In 2016 one maintainer unpublished eleven lines and broke builds worldwide. The axios and node-ipc attacks reuse that same mechanism.
Aug 3, 2026
Safety & Ethics
How does the ACE benchmark measure AI agent security?
Fabraix's ACE benchmark (April 2026) measures what an AI attacker spends to make an agent call a forbidden tool: on average $0.23 to $10.21.
Apr 11, 2026
Safety & Ethics
How are AI agents finding zero-days at scale?
By April 2026, AI tools found real vulnerabilities in open source, and the Linux kernel and curl went from AI slop to a flood of real reports.
Apr 4, 2026
Agentic AI
What did the leaked Claude Code source reveal?
Claude Code's source leaked via npm in March 2026. It showed how Anthropic's agent handles memory and subagents, and features that had not shipped yet.
Apr 4, 2026