Prompt Security detects and protects against prompt injection, sensitive data exposure, and other AI security threats.
Admin Settings
button on SidebarPlugins
tab under Organisation SettingsGuardrails
page and click the Create
buttonAdd
actions
you want on your check, and create the Guardrail!Check Name | Description | Parameters | Supported Hooks |
---|---|---|---|
Protect Prompt | Protect a user prompt before it is sent to the LLM | None | beforeRequestHook |
Protect Response | Protect a LLM response before it is sent to the user | None | afterRequestHook |
before_request_hooks
or after_request_hooks
params in your Portkey Config