Poisoning the Toolbelt: The Hidden Risks of AI Agent Skills
A new security framework reveals how reusable 'skills' in AI agents create a new attack surface for data theft and unauthorized system access.
Category
A new security framework reveals how reusable 'skills' in AI agents create a new attack surface for data theft and unauthorized system access.
A critical vulnerability in GitHub Enterprise Server allowed attackers to execute code remotely via malformed Git hooks, threatening the security of internal corporate codebases.
A critical Remote Code Execution vulnerability in GitHub Actions allowed attackers to hijack runners through malicious pull requests, threatening private repository secrets.
Five specific pieces of hardware that each close a concrete attack path for normal people. No subscriptions, no yearly fees, around 250 euros all-in.
SMS and authenticator-app 2FA looks like security but leaves a trivial opening. A 50-dollar piece of hardware closes it — and almost nothing else will.