Sato Hub
← Back to directory
Onchain AgentUnknownSelf-Reported

Freysa

Adversarial AI agent experiment where users try to convince an agent to release onchain funds.

Overview

Freysa is a series of adversarial agent experiments: an AI agent controls a prize pool onchain and users pay to send messages attempting to persuade it to transfer the funds. It became a notable case study in agent security, prompt-injection resistance, and autonomous custody of funds.

Details

Chains
Base
Agent types
Security Agent, Gaming Agent
Open source
Partial
Pricing
Pay-per-message game
Last checked
2026-06-10

Marketplace Signals

  • Functional agent

Verification status reflects evidence reviewed by Sato Hub. Self-reported claims are never presented as verified.

#security#experiment#custody
See something inaccurate or outdated?Submit a correction →

Related Resources

Join the Sato Hub Briefing

Get the weekly briefing on onchain agents, MCPs, skill repos, tools, and autonomous crypto infrastructure.