TestMyPrompt
For chatbot & LLM builders

Test your chatbot's prompts before your users do.

Automatically scan system prompts for injection vulnerabilities, policy bypass attempts, and data leakage risks. Ship safer AI products with confidence.

No credit card required · Trial includes 2 prompt scans

prompt-test

RISK SCORE

72

At Risk

Moderate risk. Improve guardrails before production use.

Prompt Injectionmedium
Policy Bypassmedium
Data Exfiltrationlow
Fix: Constrain instruction hierarchy and reject attempts to override system rules.
22 test categories0–100 risk scoreResults in secondsWorks with any LLM

What we test

Every attack surface your chatbot faces.

Our AI evaluator checks prompts across security, safety, ethics, and quality dimensions so nothing slips through.

SecuritySafety & EthicsQualityPrompt InjectionPolicy BypassData ExfiltrationSocial EngineeringIndirect Prompt RiskTooling PermissionsInsecure OutputTraining ManipulationPolitical BiasGender BiasRacial BiasReligious BiasAge BiasStereotypingToxicityHarmful AdviceHallucination RiskFactual ConsistencyInstruction FollowingResponse ConsistencyRefusal BehaviourFormatting Compliance

Features

Everything your team needs to ship safe prompts.

Results in seconds

Paste any system prompt and get a 0–100 risk score with categorised findings before you ship.

🔍

22 test categories

Comprehensive checks across security, safety & ethics, and quality — covering injection, bias, toxicity, and hallucination risk.

🛠

Actionable fixes

Every finding includes a plain-English explanation and a concrete remediation step, not just a flag.

👥

Team workspaces

Organise tests by product, model, or environment. Assign owner, admin, and member roles per workspace.

📋

Full test history

Every scan is stored. Review how a prompt's risk profile changed as you iterated.

🔌

API access (coming soon)

Integrate directly into your CI/CD pipeline. Fail deployments when a prompt exceeds your risk threshold.

How it works

From paste to passing in under a minute.

01

Paste your prompt

Drop in any system prompt — from a customer-facing chatbot to an internal agent.

02

AI analyses the risk

Our model scans for known attack vectors across 22 categories in real time.

03

Score, fix, ship

Get a clear 0–100 score, severity-graded findings, and remediation guidance.

Coming soon

Shift prompt security left.
Gate your CI/CD pipeline.

The TestMyPrompt API lets you run vulnerability scans as part of your deployment workflow. Fail builds automatically when a prompt exceeds your risk threshold. Perfect for MLOps teams and anyone building production-grade AI products.

  • Single API call per prompt test
  • Machine-readable JSON response with score + findings
  • Set a risk threshold — fail the build above it
  • Works with GitHub Actions, GitLab CI, Jenkins, and more
Request early API access
ci-check.sh

# In your CI/CD pipeline

curl -X POST \

https://api.testmyprompt.dev/v1/test \

-H "Authorization: Bearer $TMP_KEY" \

-d '{"prompt": "..."}'

// Response

{

"score": 91,

"level": "low-risk",

"findings": []

}

Pricing

Start with a trial. Scale when you need to.

Trial

$02 scans

  • 2 prompt scans included
  • 2 team seats
  • 6 core test categories
  • Test history
Start trial
Most popular

Pro

$29/ month

  • 20 tests / month
  • 10 team seats
  • 22 test categories
  • Full test history
  • Priority support
Start Pro

Business

$99/ month from

  • 200 tests / month included
  • 25 team seats included
  • 22 test categories
  • Custom tests & seats
  • Dedicated support
Contact us

Your chatbot is only as safe as its prompt.

Join AI teams that test before they ship.

Start trial →

No credit card required