Skip to main content
Skills declare what they need access to. Permissions are shown to users before install.
PermissionWhat It Allows
read:conversationsAccess conversation history
read:artifactsRead generated files and images
write:artifactsCreate and store files
write:notesCreate user-visible notes
external:httpMake outbound HTTP requests
execute:toolsCall the skill’s declared tools
autonomous:runExecute without user in the loop

Enforcement

  • Skills without execute:tools have their tools stripped at load time
  • Skills without declared permissions operate in legacy mode (all tools allowed)
  • Permission combinations that grant broad write or external-network access are promoted to a higher review tier during submission