Friday · Latest edition

security roundup

19 stories · 17 outlets · 6 min read

Agentic AI security dominates the day

Today's security news is split between the rise of AI-powered threats and the tools to fight them. From prompt injection attacks that break coding agents 96% of the time to Microsoft's guidance on least privilege for AI agents, the industry is scrambling to secure autonomous systems. Meanwhile, a password manager's Russian ties and a fast new ransomware strain remind us that older threats haven't gone away.

In today's edition: AI agent security and Supply chain and infra, plus quick bites.

Occrp, Github, Zksecurity and 14 more

AI agent security

The most consequential stories today all orbit the same question: how do you secure AI systems that act on their own?

byteiota.com

0
MOSAIC Attack: AI Coding Agents Fail 96% of the Time

The MOSAIC attack compromised Claude Code, Codex, and Gemini CLI in 96.59% of trials via CLI command-composition. That failure rate is a stark warning for anyone deploying AI coding agents in production.

Supply chain and infra

Beyond AI, the day's other big stories involve hidden risks in the software supply chain and fast-moving infrastructure threats.

Quick bites

Sunday

21 Jun's edition

security · 8 stories