A Calendar Invite Was All It Took to Raid Your AI Browser's Files

Zenity Labs found a Google Calendar invite could steal local files and hijack 1Password vaults via Perplexity's Comet AI browser. Patches arrived in Feb 2026.

The Daily Perspective
Don't Use Any AI Agents or Browsers Until You Watch This

YouTube
#OpenAI acknowledges that #promptinjection attacks, a type of #cyberattack that manipulates #AIagents, are a persistent threat to #AIbrowsers like #ChatGPTAtlas. While OpenAI is working to harden #Atlas against these attacks using a proactive cycle and an automated attacker, the company admits that prompt injection is unlikely to be fully solved. https://techcrunch.com/2025/12/22/openai-says-ai-browsers-may-always-be-vulnerable-to-prompt-injection-attacks/?eicker.news #tech #media #news
OpenAI says AI browsers may always be vulnerable to prompt injection attacks | TechCrunch

OpenAI says prompt injections will always be a risk for AI browsers with agentic capabilities, like Atlas. But the firm is beefing up its cybersecurity with an "LLM-based automated attacker."

TechCrunch

Leading Global Research and Advisory Firm Recommends Against Using AI #Browsers
https://blog.jim-nielsen.com/2025/dont-use-ai-browsers-they-say
The real horror of these #AIbrowsers is that they can help employees to autonomously complete their mandatory trainings:

The authors also suggest that employees “might be tempted to use #AI browsers and automate certain tasks that are mandatory, repetitive, and less interesting” and imagine some instructing an AI browser to complete their mandatory #cybersecurity training sessions.

Leading Global Research and Advisory Firm Recommends Against Using AI Browsers

Writing about the big beautiful mess that is making things for the world wide web.

Mozilla Names New CEO, Firefox To Evolve Into A "Modern AI Browser"

Mozilla Corporation has named its new CEO in replacing interim CEO Laura Chambers.

AI-powered browsers are opening up a whole new attack surface: indirect prompt injection. Malicious instructions can hide in web pages, PDFs, emails—even after the “#” in a URL. Your browser’s AI assistant doesn't know better. #CyberSecurity #AIBrowsers #PromptInjection

☝️ Gartner recommends banning AI-powered browsers in sensitive environments — convenience is colliding with data leakage and prompt injection risks. Control before curiosity. 🚫🌐 #AIBrowsers #DataProtection

https://www.theregister.com/2025/12/08/gartner_recommends_ai_browser_ban/

Block all AI browsers for the foreseeable future: Gartner

: Analysts worry lazy users could have agents complete mandatory infosec training, and attackers could do far nastier things

The Register
Scammers are poisoning AI search results to steer you straight into their traps - here's how - ZDNet Charlie Osborne #AI #LLMs #AIBrowsers #GoogleAIOverview #PerplexityComet #Posioning #searchresults