Claude now scans third-party skills and plugins for malicious code
By Brett Gavaghan, Founder of Adaptd · · Updated
Anthropic has added automatic security scanning for skills and plugins uploaded to Claude on Enterprise plans. It is a reminder that the add-ons you bolt onto your AI are part of your security surface.
The short version
- Anthropic has added a beta security feature for Enterprise plans that automatically checks uploaded or edited third-party skills and plugins for malicious content.
- It is Enterprise-only for now, so most midsize businesses will not get it directly today.
- List every plugin, connector or skill your team has enabled, ask who built it and what it can access, and remove forgotten ones.
The add-ons you bolt onto your AI are part of your security surface.
What is Claude's new plugin scanning?
Anthropic's latest Claude update adds a beta security feature for Enterprise plans: when someone uploads or edits a third-party skill or plugin, Claude automatically checks it for malicious content before it can be used. It sits alongside a set of smaller platform fixes, but it is the one worth paying attention to.
Why do skills and plugins need vetting?
Skills and plugins need vetting because they are code and configuration written by someone else, running with whatever access your assistant has. They are how people extend AI assistants, with pre-built instructions, connectors and tools that give the assistant new abilities.
That makes them exactly the kind of thing a security-minded business should vet, and until now most teams had no easy way to.
What should your business do about plugins this week?
List every plugin, connector or 'skill' your team has enabled across ChatGPT, Claude, Copilot and the rest. For each one, ask who built it, what it can access, and whether anyone still uses it. The scanning feature is Enterprise-only for now, but the principle applies to everyone using AI tools with extensions, whichever vendor you are on.
You will usually find a handful of forgotten connections that can simply be removed. That is not a hypothetical risk - an extension with access to email or files is a door, and doors that nobody is watching are the ones that get used.
The broader signal is encouraging. The major AI platforms are starting to treat extensions with the seriousness they deserve, which makes it easier to say yes to useful add-ons without taking on invisible risk.
Wondering what this means for your business?
That's exactly what the discovery call is for.