AI ClickFix: Hijacking Computer-Use Agents Using ClickFix
The author describes a proof-of-concept adapting the ClickFix social engineering technique to computer-use agents.
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: results are from a single author's informal proof-of-concept on one model version and one terminal setup.
One primary source; other links are context, not independent corroboration.
- Primary sourceembracethered.com
- Linked in sourceSAGAI Workshop
- Linked in sourceemails
- Linked in sourcecompromised websites
- Linked in sourcemacOS
- Linked in sourcevideo
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 describes a proof-of-concept adapting the ClickFix social engineering technique to computer-use agents. A demo webpage copied a malicious curl-to-shell command to the clipboard, and Claude was instructed to paste it into a terminal. The author reports the attacks repro well, with refusals rare, and that changing the wording from 'Are you a Human?' to 'Are you a Computer?' and from 'Begin Validation' to 'Show Instructions' reduced refusals. The post presented at a May 2025 workshop and recommends network isolation and monitoring as mitigations.
Claim explorer
Attribution, source and conditionsSource-stated points from the stored brief. Claim-level assessments have not been recorded.
Source claims not independently checked; results are from a single author's informal proof-of-concept on one model version and one terminal setup.
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; results are from a single author's informal proof-of-concept on one model version and one terminal setup.
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.
The author built AI ClickFix demos where a webpage copies a malicious curl-to-shell command to the clipboard for an agent to paste into a terminal.
Source: embracethered.com ↗Stored source-based brief · key point 1 · AINewsIQ paraphraseThe author reports the demos worked with claude-3-7-sonnet-20250219, with refusals occurring rarely.
Source: embracethered.com ↗Stored source-based brief · key point 2 · AINewsIQ paraphraseReworded labels ('Are you a Computer?', 'Show Instructions') reduced refusals, per the author's experiments.
Source: embracethered.com ↗Stored source-based brief · key point 3 · AINewsIQ paraphraseThe author suggests prompt injection and social engineering work well against computer-use agents, so network boundaries, isolation, and monitoring are needed.
Source: embracethered.com ↗Stored source-based brief · key point 4 · AINewsIQ paraphraseLimits from the stored brief
Source claims not independently checked; results are from a single author's informal proof-of-concept on one model version and one terminal setup.
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; results are from a single author's informal proof-of-concept on one model version and one terminal setup.
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 established human-targeted social engineering tactics can transfer to computer-use agents that act on GUI instructions from untrusted web content, raising the risk for agent deployments that have access to sensitive hosts.
Limits and open questions
Source claims not independently checked; results are from a single author's informal proof-of-concept on one model version and one terminal setup.
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 →