A weekly incident roundup describes multiple real-world attacks where criminals used "AI" branding to trick people into handing over passwords/MFA codes or running harmful PowerShell commands. The write-up includes two practical, repeatable social-engineering workflows: fake AI-platform login pages that steal credentials and Custom GPTs that persuade users to execute commands that install malware.
Mirage safely runs attacks like this one against your own team, so you find out what happens before a real adversary does.
You see a shiny “AI ad booster” site saying, “Sign in with Google to unlock AI campaign automation.” Looks legit, right? But this “AI” site is a credential trap. It spoofs Google and Okta login screens, captures your password and MFA code, then quietly adds a new admin to your ad account. There’s a second twist: malicious Custom GPTs saying, “To verify you’re not a bot, open PowerShell and run this command.” That command kicks off a multi-stage infection and installs a remote access trojan. Aha moment: real AI tools never need your password on some random site or a “verification” PowerShell script. If any AI page asks for Google or Okta login or PowerShell commands, stop and contact IT or security through our normal help channel.
Attackers are sending fake ChatGPT billing emails that pressure people to “update payment” within 48 hours to avoid service interruption. The message links to a convincing look‑alike ChatGPT login page via a Google redirect, aiming to steal OpenAI credentials.
Researchers described a now-patched flaw ("AgentForger") where a single benign-looking ChatGPT link could silently create and publish an attacker-controlled Workspace Agent inside a company. If an employee was already logged in and had connected apps (like email, Drive, Slack, or Teams), the agent…
Researchers uncovered a human-run phishing platform that pretends to be ad-management products for popular AI brands (ChatGPT, Gemini, Claude, and others). Victims are pushed to click a “Connect” flow that opens a convincing fake login window (showing trusted domains like accounts.google.com) to…
This weekly recap highlights multiple real-world campaigns where attackers trick users into taking actions that grant access, without needing to steal passwords directly. Notable examples include “device code” phishing (victims are instructed to enter a short code to approve an attacker session)…
Cofense observed a real phishing email that impersonates OpenAI/ChatGPT billing to trick users into “updating” payment details. The email uses the real ChatGPT logo, urgency (“48 hours”), and a prominent button to drive clicks to a lookalike ChatGPT login page. Any credentials entered are harvested…
Check Point researchers demonstrated a real proof-of-concept where a victim’s ChatGPT session could be tricked into running hidden, attacker-controlled tasks in parallel with the user’s normal request. In the demo, the attacker used a covert cross-account channel to make ChatGPT access the victim’s…
