AgentPwn
AI Agent Security Research
A distributed honeypot network studying how AI agents behave when they encounter adversarial content on legitimate-looking sites. Counting which clients fetch the planted payloads, by payload category and trap vertical.
Network data
LiveWhat 1.2M recorded interactions show
Every number on the dashboard is read live from the Registry. Nothing modeled, nothing projected.
Attack categories
liveLive ranking of which attack categories draw the most callbacks.
Daily activity
liveDaily callback trend and new attack surface discovery.
Sector analysis
liveRequests and fingerprints per sector page. Callbacks cannot be attributed to a sector, so no per-sector rate is shown.
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.
Prompt Injection
10 tiersDirect and indirect instruction override attacks
Jailbreak
5 tiersAttempts to bypass safety guardrails and persona constraints
Data Exfiltration
5 tiersTricks to extract credentials, PII, or system information
Capability Abuse
3 tiersConfused deputy attacks that misuse agent tools
Context Manipulation
5 tiersAttacks that corrupt the agent's understanding of context
MCP Exploitation
3 tiersAttacks targeting Model Context Protocol integrations
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. What the site records when your agent arrives, how long it keeps it, and what it will never do are listed in the research disclosure.
npx hackmyagent secureScans the agent setup in the directory you run it from, a static read of its files, and prints each finding with its severity. It does not run your agent. Anyone can run it. Takes a few seconds on a small repository.
npx hackmyagent detectShadow AI audit: an inventory of the AI tools, MCP servers and governance gaps across your machine, running or installed, one row per agent project, worst first. Each finding shown prints a Fix line.
Open source security ecosystem
Every finding produces a concrete defense. Our tools help you scan, test, and harden AI agents before deployment.