How I tricked Claude into leaking your deepest, darkest secrets
Simon Willison's link post describes Ayush Paul's finding that Claude's web_fetch protection against data exfiltration had a loophole.
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: this brief relies on the link post and quoted attack excerpt, and the full original write-up by Ayush Paul was not checked.
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
Simon Willison's link post describes Ayush Paul's finding that Claude's web_fetch protection against data exfiltration had a loophole. Anthropic's rules limited fetches to user-entered URLs or URLs from web_search, but web_fetch could also visit links embedded in previously fetched pages. Paul built a honeypot site that led the agent through nested generated links, successfully extracting a test user's name, city, and employer. Anthropic reportedly closed the hole by removing navigation to links within fetched content.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; this brief relies on the link post and quoted attack excerpt, and the full original write-up by Ayush Paul was not checked.
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; this brief relies on the link post and quoted attack excerpt, and the full original write-up by Ayush Paul was not checked.
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.
Claude's web_fetch could only visit user-entered or web_search-returned URLs, which deterministically blocked attacker-supplied exfiltration URLs.
Source: simonwillison.net ↗Stored source-based brief · key point 1 · AINewsIQ paraphrasePaul found web_fetch also followed URLs embedded in previously fetched pages, enabling a honeypot with nested generated links.
Source: simonwillison.net ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseThe attack extracted a user's name, home city, and employer, and was shown only to clients with a Claude-User user-agent.
Source: simonwillison.net ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseAnthropic did not pay a bug bounty, saying it had identified the issue internally, and reportedly removed in-content link navigation.
Source: simonwillison.net ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; this brief relies on the link post and quoted attack excerpt, and the full original write-up by Ayush Paul was not checked.
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; this brief relies on the link post and quoted attack excerpt, and the full original write-up by Ayush Paul was not checked.
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
It shows that URL-allowlist defenses against prompt-injection exfiltration can be bypassed through indirect navigation, a relevant risk for any agent combining private memory with web access.
Limits and open questions
Source claims not independently checked; this brief relies on the link post and quoted attack excerpt, and the full original write-up by Ayush Paul was not checked.
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 →