AINewsIQ by Triuna Labs
Menu
SOURCE-LINKED SIGNAL / ARTICLE / SAFETY & EVALS

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.

READ THE ORIGINAL SOURCEOpen original sourcesimonwillison.net UTC

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.

Recorded links

One primary source; other links are context, not independent corroboration.

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 →
How this score was derived
  • 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 conditions

Source-stated points from the stored brief. Claim-level assessments have not been recorded.

About 6,000 attempts to leak secrets from the test assistant via email failed.
Source assertionNot independently checked
Primary sourcesimonwillison.netInspect source ↗
Attributed toClaimant not recorded per pointSource assertion
Conditions / limitsClaim-specific conditions not recorded. Read the source and limits below.

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 reporting
What 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.

Limits 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.

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.

Checking sign-in…

New commenters: 2 submissions per 24 hours, at least 5 minutes apart, until 3 are approved. Discussion guidelines and moderation →