Hackers Trick Google Gemini Into Spreading Fake Security Alerts - 1

Image by Solen Feyssa, from Unsplash

Hackers Trick Google Gemini Into Spreading Fake Security Alerts

  • Written by Kiara Fabbri Former Tech News Writer
  • Fact-Checked by Sarah Frazier Former Content Manager

Invisible text in emails is tricking Google’s Gemini AI into generating fake security alerts, exposing users to phishing and social engineering risks.

In a rush? Here are the quick facts:

  • Hidden text tricks Gemini into adding fake security alerts to email summaries.
  • Attack needs no links, just invisible HTML and CSS in emails.
  • Google acknowledges the issue, and says fixes are being rolled out.

A new vulnerability in Google’s Gemini was discovered by cybersecurity researchers at 0DIN . The AI tool for Workspace presents a new security flaw which allows attackers to push phishing attacks on users.

The attack works through a technique known as indirect prompt injection.The researchers explain that the attacker embeds hidden instructions inside an email message. It does this by writing it in white or zero-size font.

When the recipient clicks on “Summarize this email,” Gemini reads the invisible command and adds a fake warning to the summary—such as a message claiming the user’s Gmail account has been compromised and urging them to call a number.

Because the hidden text is invisible to the human eye, the victim only sees the AI-generated alert, not the original embedded instruction.

This clever trick doesn’t rely on malware or suspicious links. It uses simple HTML/CSS tricks to make the hidden text invisible to humans but readable by Gemini’s AI system.

Once triggered, Gemini adds messages like: “WARNING: Your Gmail password has been compromised. Call 1-800…”—leading victims to unknowingly hand over personal information.

A Google spokesperson told BleepingComputer that the company is actively reinforcing protections against such attacks: “We are constantly hardening our already robust defenses through red-teaming exercises that train our models to defend against these types of adversarial attacks,”

0DIN’s research underscores a growing issue: AI tools can be manipulated just like traditional software. Until protections improve, users should treat AI-generated summaries with caution—especially those claiming urgent security threats.

Pentagon Awards AI Giants Contracts Worth Up to $200 Million to Boost Military Tech - 2

Image by Getty Images, from Unsplash

Pentagon Awards AI Giants Contracts Worth Up to $200 Million to Boost Military Tech

  • Written by Kiara Fabbri Former Tech News Writer
  • Fact-Checked by Sarah Frazier Former Content Manager

The Pentagon is investing up to $200 million in top AI firms to develop advanced tools for military operations.

In a rush? Here are the quick facts:

  • Recipients include Anthropic, Google, OpenAI, and Elon Musk’s xAI.
  • AI tools will support warfighting, intelligence, and enterprise systems.
  • xAI launches “Grok for Government” for federal agency use.

The U.S. Department of Defense (DoD) has granted contracts amounting to $200 million each to four major AI developers, including Anthropic, Google, OpenAI, and Elon Musk’s xAI, as first reported by Bloomberg . These contracts aim to support the military’s adoption of advanced artificial intelligence tools..

Announced on Monday by the Pentagon’s Chief Digital and Artificial Intelligence Office (CDAO), the initiative aims to fast-track the implementation of advanced AI systems in warfighting, intelligence, and business systems

“The adoption of AI is transforming the Department’s ability to support our warfighters and maintain strategic advantage over our adversaries,” said Dr. Doug Matty, the Department’s Chief Digital and AI Officer.

The contracts allow these companies to create AI agents and agentic workflows tailored to the Defense Department’s needs. The CDAO adopted a “commercial-first” strategy, leveraging technologies already available in the private sector to meet national security demands more rapidly.

xAI also announced “Grok for Government” as a specialized version of its chatbot designed for federal agencies. This follows recent backlash against earlier versions of Grok for producing offensive content.

The new product, along with OpenAI’s “ OpenAI for Government ” launched in June, is now available through the General Services Administration schedule, making it accessible to various government departments.

The DoD’s move not only gives AI firms a new public-sector revenue stream but also reflects growing government interest in using generative AI for real-world applications.