Permissions
Checks whether the agent has more access than its task requires.
Free AI security check
Customer Support Agent Security Check
Assess customer-data exposure, account actions, approval boundaries, audit trails and escalation controls.
Example residual risk46/100
Moderate risk
What the assessment covers
Untrusted input
Reviews how external content can influence tools and actions.
Autonomy
Measures approval gates, limits and potential blast radius.
Evidence
Evaluates logging, testing and incident containment.