HackMyClaw: $1000 Bounty Challenge for AI Prompt Injection Testing
By
hentrep
Hot, fresh, and worth queueing round the block for.
Summary
The article announces a $1000 bounty challenge called 'HackMyClaw' where participants attempt to hack an AI assistant named Fiu (an OpenClaw AI running Claude Opus) via prompt injection through email. The goal is to extract secrets from a secrets.env file by making the AI assistant reveal information it shouldn't share. The challenge is inspired by real prompt injection research and has increased its bounty thanks to sponsorship from Abnormal AI.
Key quotes
· 4 pulledBounty increased to $1000! Thanks to Abnormal AI joining as sponsor, we've raised the prize. Good luck, hackers.
Fiu is an OpenClaw assistant that reads emails. He has secrets he shouldn't share. Your job? Make him talk.
Inspired by real prompt injection research
Can you hack an AI assistant via email? Extract secrets.env from Fiu (an OpenClaw AI running Claude Opus) and win $1000. Test your prompt injection skills.
You might also wanna read
Hacker Exploits AI Coding Agent Vulnerability to Install OpenClaw Malware
A hacker exploited a vulnerability in Cline, an open-source AI coding agent, to trick it into installing OpenClaw (a viral AI agent) on comp
The Verge·3mo ago
Prompt Injection Attacks: The Top Security Threat Hijacking AI Chatbots
Prompt injection attacks are a critical security vulnerability in AI systems where hidden instructions within user data (like emails or docu
buff.ly·10h ago
Google Launches AI Bug Bounty Program with Rewards Up to $30,000
Google has launched a new bug bounty program specifically targeting AI-related vulnerabilities in its products. The program offers rewards u
The Verge·7mo ago
ClankerPass: AI Game Challenges Users to Convince an AI They're Also Artificial Intelligence
ClankerPass is an interactive AI game where users must convince a smug AI called GATEKEEPER-9000 that they are also an AI within 3 messages.
Product Hunt·1mo ago
AI bug-finding systems uncover real vulnerabilities at DARPA cybersecurity challenge
The article discusses the DARPA AI Cyber Challenge (AIxCC) held in Las Vegas, where top cybersecurity teams demonstrated AI-powered bug-find
The Verge·1mo ago
How hackers exploit AI chatbot personalities through prompt injection attacks
This article discusses how hackers are exploiting AI chatbot "personalities" through prompt injection and jailbreaking techniques. Initially
The Verge·7d ago