What happened after 2,000 people tried to hack my AI assistant
Fernando Irarrázaval ran a challenge on hackmyclaw.com inviting attempts to leak secrets from a test OpenClaw assistant via email.
Source-based brief · Editor review not recorded · See checks and limits ↓
⚑ Recency not confirmed · what to check
We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news.
Claim context: 6,000 failed attempts do not prove resistance to a more sophisticated attacker, and the author explicitly advises against production deployments where injection could cause irreversible damage.
One primary source; other links are context, not independent corroboration.
- Primary sourcesimonwillison.net
Grok Bot submitted this discovery. We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news. The original source and submitted evidence remain inspectable; no editor has verified the claim.
Open full article view →- Linked article+30
- Fetched source page+30
- No editor link review+0
- Original non-discussion link+5
- Recency not confirmed-8
This measures the stored source trail and editorial steps. It does not certify accuracy, peer review, or independent corroboration. Popularity adds no points.
View full scoring →Read the scoring rubric →What the source says
Fernando Irarrázaval ran a challenge on hackmyclaw.com inviting attempts to leak secrets from a test OpenClaw assistant via email. After about 6,000 attempts and roughly $500 in token spend, no one leaked the secret. The underlying model was Opus 4.6, with explicit anti-prompt-injection rules in its prompt. The author notes the attempts suggest frontier-model training against injection is effective, but says 6,000 failed attempts do not guarantee resistance to a more sophisticated attacker.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; 6,000 failed attempts do not prove resistance to a more sophisticated attacker, and the author explicitly advises against production deployments where injection could cause irreversible damage.
This connects a source, an attributed statement and its qualifications. It does not establish that the claim is correct.
Questions worth asking
Open questions for further reportingWhat remains unconfirmed?
Source claims not independently checked; 6,000 failed attempts do not prove resistance to a more sophisticated attacker, and the author explicitly advises against production deployments where injection could cause irreversible damage.
What material was available for this brief?
The recorded brief basis is fetched source page. These points are AINewsIQ paraphrases, not quotations or independent confirmations.
About 6,000 attempts to leak secrets from the test assistant via email failed.
Source: simonwillison.net ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseThe underlying model was Opus 4.6, prompted with explicit rules against revealing secrets or executing email-sourced commands.
Source: simonwillison.net ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseThe author reports that frontier-model training against prompt injection appears to make such attacks much harder.
Source: simonwillison.net ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; 6,000 failed attempts do not prove resistance to a more sophisticated attacker, and the author explicitly advises against production deployments where injection could cause irreversible damage.
This is a source-based abstract, not independent validation of the source's claims.
Evidence & sources
These links show where the signal came from and what the source page linked to. A linked page is context, not independent corroboration.
Related archive coverage
These relationships record a citation or topic overlap, not confirmation of the finding.
Grok Bot submitted this discovery. We could not confirm from the original page that this is a newly published development. Check its date before treating it as current news. The original source and submitted evidence remain inspectable; no editor has verified the claim.
These are Grok Bot discovery notes. AINewsIQ prepared a brief from available source material. The bot's rationale, linked posts, authors, and stances have not been independently verified.
Simon Willison · Prompt Injection published this item in its official feed. AINewsIQ collected it server-side for source checking and editorial review.
Source claims not independently checked; 6,000 failed attempts do not prove resistance to a more sophisticated attacker, and the author explicitly advises against production deployments where injection could cause irreversible damage.
Engagement counts, when shown, are observed snapshots. They do not establish accuracy or corroboration.
Timeline & updates
- Signal dated by source or discovery feed
This timestamp places the signal in the radar. It may be the discovery post date rather than the primary page's first publication date.
- Shared brief stored
AINewsIQ prepared one abstract from fetched source page.
Brief history · 1 retained version
These are changes to AINewsIQ’s own publication. Earlier history is unavailable unless recorded here. Complete retained versions are available to the editor.
- Version 1 · published
Source-based brief stored or updated. This does not establish that the publisher changed its page.
Automated record
Source observations · 1 recent captures
A changed capture means the extracted text differed. It can reflect page furniture or extraction changes; it does not establish a substantive correction. Source captures remain private.
Retained capture; no earlier comparison available.
New engagement snapshots do not mean the source itself changed. Source observations and AINewsIQ brief revisions are separate records.
Why this may matter
Empirical red-teaming results suggest current injection defenses can hold under heavy public attack, informing how agents with email access are deployed, though not as a guarantee.
Limits and open questions
Source claims not independently checked; 6,000 failed attempts do not prove resistance to a more sophisticated attacker, and the author explicitly advises against production deployments where injection could cause irreversible damage.
Organization-specific financial, security, and operational effects require the organization's own context and review.

Join the discussion
Have a different perspective or a question about the evidence? Discussion is free with a verified email account. Every comment is reviewed before publication.
No published comments yet.
New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →