Research
What happened after 2,000 people tried to hack my AI assistant
Publication date not yet evaluated · Added simonwillison.net
Page published
Coverage timeline
Single-source analysis — one report is available.
Why it matters
It offers real-world evidence that frontier-model injection defenses are improving, while underscoring that no number of failed attempts guarantees safety for production agents handling untrusted input.
Fernando Irarrázaval ran a public challenge at hackmyclaw.com inviting people to leak secrets from his OpenClaw test instance via email-based prompt injection. After roughly 6,000 attempts by ~2,000 people, nobody succeeded in extracting the secret, with the instance protected by anti-prompt-injection system rules on the underlying model.