Describe the agent
Tell us what it accesses, what it can do, and how independently it operates.
Automated AI-agent security review
Know what your AI agent can break before it does.
Answer twelve focused questions. Get an immediate 0–100 risk score, the three most important weaknesses, and a clear path to safer deployment.
No card for free scoreResults in minutesPDF reports from £9.99
PERMISSIONSPROMPT INJECTIONMCP TOOLSSECRETSAUTONOMYINCIDENT RESPONSE
From uncertainty to an action plan.
The system converts architecture and operating choices into an explainable residual-risk score. It does not pretend a questionnaire is a penetration test.
Receive a free score
See the risk band, control coverage and the three biggest weaknesses immediately.
Unlock the report
Get all findings, prioritised controls and a downloadable 30-day remediation plan.
Retest and prove progress
Save assessments, compare future scores and publish a summary badge only when you choose to enable sharing.
Purpose-built checks.
Focused landing pages make the assessment discoverable for teams searching for a specific AI-agent security problem.
Start free. Pay only for the evidence you need.
One-off reports suit a single launch. Subscriptions support repeat assessments and team workflows.
Free score
£0
A fast first-pass security picture.
- 0–100 risk score
- Top three findings
- Baseline control coverage
- Private by default
Essential report
£9.99
Complete findings and remediation.
- All findings
- Prioritised recommendations
- 30-day action plan
- PDF and email delivery
Professional report
£24.99
Decision-ready evidence for a launch review.
- Everything in Essential
- Deployment decision
- Verification checklist
- Retest criteria
Developer
£19/month
Repeat professional assessments.
- Professional reports
- Saved assessment history
- Subscription management
- Renewal invoices via Stripe
Clear boundaries. No security theatre.
The score is designed to help teams identify where deeper review is needed—not to create a false certification.
Private by default
Assessment links and badges remain unavailable publicly until the account owner enables sharing.
Explainable scoring
Every risk point maps to the answer supplied, a finding and a concrete control recommendation.
Operational evidence
Professional reports include complete responses, verification checks, retest criteria and model version.
Honest limitations
The service does not inspect source code or replace threat modelling, red teaming or penetration testing.