How online search and AI can install malware

[MevetS]

We live in scary times. Another attack vector like these previous ones noted on the forum. How many more yet to come?

---

ClickFix Malware

I’m assuming we’ve all heard about ClickFix malware and how it works by tricking you into copying something into your clipboard. Has anyone found a simple, clear explanation to share with family and friends about the attack vector? It is a hard one to explain to non-technical people. Especially since in some cases people are getting emails about legitimate hotels bookings warning them that there is a problem.

---

“Mysterious Aura,” Seriously?

Prompt injection is not something being better informed can always help with, unless you don’t use LLMs at all. From: What Is a Prompt Injection Attack? | IBM Indirect prompt injections In these attacks, hackers hide their payloads in the data the LLM consumes, such as by planting prompts on web pages the LLM might read. For example, an attacker could post a malicious prompt to a forum, telling LLMs to direct their users to a phishing website. When someone uses an LLM to read and summar…

---

Things will get worse before they get better.