Top all-time · #8518
Guardio
Company blog · guard.io/blogsecurity
Guardio is the company blog at guard.io, writing about security. Since 2019, 9 different Hacker News readers have linked it 11 times, most often “Scamlexity: When agentic AI browsers get scammed”. No feed was found, so read it on the site itself.
Too few sampled comments (2) to say how often HN recommends it.?
Why HN links it
HN readers link Guardio Labs research on agentic AI browsers, such as ChatGPT Atlas, and the scam and prompt-injection risks they create, including attacks through in-context commands.
Summarised by Claude from a sample of 2 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Protect all your devices online. Keep your personal and business data safe from phishing, malware, and identity theft. Get your free Guardio security scan today.
Most-linked posts?
- Scamlexity: When agentic AI browsers get scammed5 people · 5 mentions · first linked 2025-08-21
- Evernote could be exploited by hackers to access all your cloud services2 people · 2 mentions · first linked 2019-06-12
What Hacker News says?
> acting like a firewall between the user and web. A firewall which can set the user on fire. https://guard.io/labs/scamlexity-we-put-agentic-ai-browsers-...
Comment linking /labs/scamlexity-we-put-agentic-ai-browsers-to-the-test-they-clicked-they-paid-they-failed
on “ChatGPT Atlas”Submitted Scamlexity: When agentic AI browsers get scammed as a story · 204 points
HN discussionHow are you handling the attack vector of in-context commands[1]? [1]: https://guard.io/labs/scamlexity-we-put-agentic-ai-browsers-... (currently on the front page)
Comment linking /labs/scamlexity-we-put-agentic-ai-browsers-to-the-test-they-clicked-they-paid-they-failed
on “Launch HN: April (YC S25) – Voice AI to manage your email and calendar”Submitted USPS jumps to first place as most imitated brand in phishing attacks as a story · 70 points
HN discussionSubmitted Scamlexity as a story · 14 points
HN discussionSubmitted Evernote could be exploited by hackers to access all your cloud services as a story · 13 points
HN discussionSubmitted We Put Agentic AI Browsers to the Test – They Clicked, They Paid, They Failed as a story · 5 points
HN discussionSubmitted Hunting Down the Google-Sent Phishing Wave Compromising 30k Facebook Accounts as a story · 2 points
HN discussionSubmitted Meta tops the list as the most imitated brand in phishing attacks as a story · 1 points
HN discussionSubmitted SubdoMailing Checker: enter a domain to see if it's compromised by SubdoMailers as a story · 1 points
HN discussionSubmitted Critical Vulnerability Discovered in Evernote Chrome Extension [Jun 19, Fixed]] as a story · 1 points
HN discussion
