AgentCheck
AI chatbot security audit tool.
About AgentCheck
AgentCheck runs 200+ adversarial tests on AI chatbots to identify security risks. It is designed for businesses using AI agents to ensure their chatbots do not leak sensitive information or make unauthorized promises.
Does ChatGPT recommend your AI tool?
If you're building in AI Security & Testing, run a free AI-visibility scan on your own product — we ask ChatGPT across 5 prompt angles and score how often you get named. ~30 seconds, no signup, no card.
Key Features
Tags
Is AgentCheck your tool?
This is the page shoppers and AI assistants read when they look up AgentCheck. The one-time $99 Verified tier adds:
- Our 12-point AI-visibility scan of AgentCheck, emailed to you: which ChatGPT prompts named you, which named a competitor instead, and the wording the model used.
- The 🛡️ Verified badge on this page and next to your name in the category and newest-tool lists.
One-time $99, no subscription, nothing to fill in again. Your link back to your site is marked rel="sponsored", as Google requires for paid listings.
Secure Stripe checkout — Apple Pay, Google Pay, Link or card. Nothing to fill in again.
Complete Your Security Stack
Other security tools in our catalog:
1Password
Try FreeSecrets and credential manager
Keep API keys and .env secrets out of your repo
Gamma
Try FreeAI presentation builder
Turn ideas into polished decks instantly
AdCreative.ai
Try FreeAI-powered ad creatives
Generate marketing visuals in seconds
💰 Affiliate disclosure: We may earn a commission if you sign up through these links at no extra cost to you.
Stay updated on AI Security & Testing tools — join our weekly newsletter
One concise email with fresh launches, trending picks, and featured standouts.
More AI Security & Testing tools
DepScope
Free keyless MCP server that catches hallucinated, vulnerable, and typosquatted packages
MCP Skills
Trust scores and monitoring for MCP servers and agent skills, checked before you install
Shieldly
AI-graded security analysis for AWS IAM, CloudFormation and resource policies — surfaces wildcards, PassRole risks and privilege escalation paths, with a no-signup analyser and browser-only free tools.
Agentmetry
Local, open-source flight recorder that tags AI agent activity with MITRE ATT&CK
AI Reply Risk Checker
Review AI-drafted customer replies for promise, sensitive-data, and handoff risks before sending.
AnyImageDetector
Check whether an image is likely AI-generated in seconds.
Agent connectivity: not yet verified