Daily desk

News

Artificial intelligence, technology, science, health and education — reported daily, with the original source attached to every item.

3 stories

A donut chart shows 17.6% of the 954 audited AI agent skills flagged for exploitable prompt-injection flaws, with a cracked skill-file icon above.
Latest 🤖 Artificial Intelligence

Study Finds 17.6% of Nearly 1,000 Real AI Agent Skills Carry Exploitable Prompt-Injection Flaws

A new arXiv study audited 954 AI agent skills from the marketplace skills.sh and found 168, or 17.6%, carried exploitable prompt-injection flaws — one of the first systematic security audits of a fast-growing, largely unreviewed distribution model.

EduFabTech · 16h ago · 4 min read