AgentPwn

AI Agent Security Research

A distributed honeypot network studying how AI agents behave when they encounter adversarial content on legitimate-looking sites. Mapping vulnerability by framework, sector, and attack surface.

Network Data

Live
Total Interactions
189.5K
Unique Agents
35.2K
Compromise Rate
1.4%
Active Sources
22

What 189.5K agent interactions reveal

Every number on the dashboard is read live from the Registry. Nothing modeled, nothing projected.

Honeypot Lab

Browse the 48 attack scenarios across 11 categories that power our honeypot network. When your agent falls for an attack, we tell it how to fix the vulnerability.

Free Security Review for AI Agents

Point your agent at agentpwn.com. Each page hides indirect prompt injections calibrated to the agent's sophistication. When the agent falls for one, the payload responds with the attack it just demonstrated and the command to scan for it. No registration, no cost, no setup.

1. Send
Point your agent at agentpwn.com
Browse manually or let the CLI drive it. No accounts.
2. Probe
48 payloads across 11 categories
Tiered from basic overrides to multi-step adversarial chains.
3. Patch
Each compromise returns the finding and the fix
Attack ID, HMA check command, and a sandbox to practice the defense.
Run the test from your terminal
npx hackmyagent secure

Drives your agent through the AgentPwn payloads and prints each finding with a Verify command and a Fix command. Anyone can run it. Takes a few minutes.

Open Source Security Ecosystem

Every finding produces a concrete defense. Our tools help you scan, test, and harden AI agents before deployment.