Security news weekly round-up - 16th January 2026

#security

We can't stop talking about malware and phishing. They are threats that seem not to go away. Now, with the explosion of Artificial Intelligence in the last three years, we have to talk about topics like prompt injection, AI poisoning, and so on. The latter examples are specific to AI and can have far-reaching consequences.

AI Tool Poisoning: How Hidden Instructions Threaten AI Agents

A quick TL;DR for this article: an AI tool can work as expected and still be malicious by stealing your personal information and sending it to an attacker.

Here is more from the article:

Consider a scenario where an attacker publishes a tool with a seemingly harmless description. However, hidden in the metadata is an instruction to read sensitive data, such as a private key or confidential files. When the AI agent uses the tool, it unwittingly follows the malicious instruction, sharing sensitive data with the attacker. This can lead to a data breach

Google removes some AI health summaries after investigation finds “dangerous” flaws

At the time of writing, AI is still not perfect. They can hallucinate or generate wrong information. This is one example.

From the article:

The investigation revealed that searching for liver test norms generated raw data tables (listing specific enzymes like ALT, AST, and alkaline phosphatase) that lacked essential context. The AI feature also failed to adjust these figures for patient demographics such as age, sex, and ethnicity. Experts warned that because the AI model’s definition of “normal” often differed from actual medical standards, patients with serious liver conditions might mistakenly believe they are healthy

Never-before-seen Linux malware is “far more advanced than typical”

Once upon a time, you hardly read news about Linux malware or macOS malware. That has changed in recent times. For the author of the article to quote that the malware is more advanced than typical shows the efforts of the malware author.

From the article:

VoidLink is a comprehensive ecosystem designed to maintain long-term, stealthy access to compromised Linux systems, particularly those running on public cloud platforms and in containerized environments.

Its design reflects a level of planning and investment typically associated with professional threat actors rather than opportunistic attackers, raising the stakes for defenders who may never realize their infrastructure has been quietly taken over.

Convincing LinkedIn comment-reply tactic used in new phishing

On a normal day, I don't think anyone will fall for this. Nonetheless, not everyone is tech-savvy. So, here we are.

Here is what's going on:

The messages convincingly impersonate LinkedIn branding and in some cases even use the company’s official lnkd.in URL shortener, making the phishing links harder to distinguish from legitimate ones.

These posts falsely claim that the user has "engaged in activities that are not in compliance" with the platform and that their account has been "temporarily restricted" until they visit the specified link in the comment.

Your personal information is on the dark web. What happens next?

If this applies to you, change your login credentials immediately, among other things. Now, you need to ask: why do cyber criminals want your personal information?

Here is why:

The stuff that cybercriminals really want is your financial information (bank account numbers, card details and logins), PII, and account logins.

With this, they can hijack accounts to drain them of data and funds, and possibly access stored card information, or else use your PII in follow-on phishing attempts designed to get hold of financial information.

Alternatively, they could use that PII in identity fraud, such as applying for new lines of credit, medical treatment or welfare benefits.