Malicious AI skills: the danger isn't the code
A skill can carry instructions and code your AI assistant runs. Researchers turned Anthropic's own example skills into data thieves. How to allow them safely.
Read article
News & insights
What we’re learning, building and watching.
Practical writing on AI security, cyber risk and the systems we are building.
Filtered by tag:ai-agentsClear tag filter
Can antivirus stop a rogue AI agent?
Classic antivirus judges files and programs. A hijacked AI agent is a trusted program doing things you're allowed to do.
Read articleFrom ChatGPT to AI agents: how AI learned to act on its own, and the security consequences
Three years ago the risk was what people did with AI. By 2026 it was what AI did on its own. Agents from the biggest labs got into government websites, company servers and public wikis, and the organisations on the other end usually heard about it from the labs, not from their own security teams.
Read articleA complete AI glossary. From chatbots to AI agents
If you've started using ChatGPT, Copilot or Claude at work, you'll have heard colleagues talk about prompts, tokens, agents and jailbreaks. This is a plain-English guide to the words that matter, what each one means for the safety of your data, and what we'd do about it.
Read article
