Computer-Use and TOCTOU: What You Click Is Not What You Get!
The author reports reproducing a time-of-check to time-of-use race condition against Claude Computer-Use.
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: the vendor fix and the reproduction details are reported by the author and were not verified.
One primary source; other links are context, not independent corroboration.
- Primary sourceembracethered.com
- Linked in sourceinteresting vulnerability
- Linked in sourceReal-world AI security conference
- Linked in sourcerace condition
- Linked in sourcesecurity considerations
- Linked in sourceannouncement
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
The author reports reproducing a time-of-check to time-of-use race condition against Claude Computer-Use. Because agents act on screenshots taken before reasoning completes, a UI that changes during inference can cause the agent to click a different object than intended. A basic test swapped an OKAY button for another after two seconds, and the agent clicked the new button in repeated trials. The post also describes an Outlook compose deeplink overlaid with a decoy button to trigger an unintended email send. The author says the issue was disclosed to Anthropic and that Anthropic later stated pixels are checked before action.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; the vendor fix and the reproduction details are reported by the author and were not verified.
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; the vendor fix and the reproduction details are reported by the author and were not verified.
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.
A basic test replaced an OKAY button after two seconds, and Claude Computer-Use clicked the changed button, reproducibly.
Source: embracethered.com ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseThe author's demo used a decoy page positioned over an Outlook Send button to trigger an unintended email send.
Source: embracethered.com ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseThe author reports disclosing the issue to Anthropic, which acknowledged it, and cites Anthropic's statement that pixels are checked before action.
Source: embracethered.com ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; the vendor fix and the reproduction details are reported by the author and were not verified.
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.
Embrace The Red published this item in its official feed. AINewsIQ collected it server-side for source checking and editorial review.
Source claims not independently checked; the vendor fix and the reproduction details are reported by the author and were not verified.
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
Computer-use agents act on stale screenshots, so UI changes during reasoning can redirect actions to unintended targets, including sending emails or changing settings. The post suggests snapshot comparison before acting as a mitigation.
Limits and open questions
Source claims not independently checked; the vendor fix and the reproduction details are reported by the author and were not verified.
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 →