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:supply-chainClear tag filter
"Sometimes the free download brings a friend." Free AI models are a new attack vector
For anyone who has downloaded a free AI model, or is about to. Researchers have shown this year how cheaply a model can be trained to leak data, and the usual checks won't catch it. Here is what's known so far, and what to check before you connect one to your files, your email or your work.
Read article
