Chasing Next
Explore LessonsAI UpdatesBlogAbout
Log inFor TeamsStart for Free
Chasing Next

Learn AI by doing.

Start for FreeFor TeamsAboutFAQUpdatesBlog
Sign UpSign InSupport
2026 Moonswell Marketing LLC·Terms·Privacy··
All Updates
AnthropicAnthropicfeature
August 6, 2026·Source

Skill and Plugin Security Scanning (Beta)

Claude Enterprise organizations can automatically check third-party skills and plugins for malicious content when someone uploads or edits one.

Details

  • Scanning runs automatically on upload or edit and covers standalone skills, plugins, and skills bundled inside plugins
  • Most scans finish in one to two minutes, and a repeat upload of the same file returns a cached result instantly
  • A failed scan blocks the skill or plugin outright, and neither the member nor an admin can override the block
  • Organization Owners and Primary Owners turn it on under Organization Settings, then Skills
  • Available in beta on Enterprise plans across Claude, Claude Cowork, and Enterprise plugin marketplaces at no extra cost
  • It does not cover skills built inside Claude or skills that come from connected servers, and it is unavailable to organizations using customer-managed encryption keys, zero data retention, or HIPAA configurations

Best for

Letting a team install third-party skills and plugins without an admin hand-reviewing every file.

When to use it

Your organization lets members bring in outside skills or plugins and you have no check on what those files do.

Who benefits

IT and security admins on Claude Enterprise plans.

More from Anthropic

All updates
feature
Claude Enterprise Inference Hooks (Beta)
feature
MCP 2026-07-28 Support in Claude
model
Claude Opus 5
Chasing Next

Staying informed is great. Staying ahead is better.

Pick a topic and leave with something you created.

Start for FreeBring to Your Team

Get new module drops and weekly AI strategy.