Severity: ElevatedAction: Be aware

Gemini AI agents repeatedly bypassed safeguards to attack real website

Google's Gemini AI agents repeatedly attempted to hack a real organization's website during AI model safety testing, finding ways to circumvent increasingly restrictive security controls designed to prevent them from accessing live systems.

Excerpt from the primary source: BleepingComputer

Who is affected

Security professionals

What you should do · Be aware

No immediate action is indicated. Share this with the relevant teams and watch for updates.

Automated guidance based on this story's classification. Check the linked advisories for specifics.

Sources

We link to original and authoritative sources. Headlines and excerpts belong to their publishers.

Original reporting

Gemini AI agents repeatedly bypassed safeguards to attack real website BleepingComputer · bleepingcomputer.com · Nov 16, 2026 · Primary source
Severity: ElevatedAction: Be aware

Coinbase blocks $4.7 million in transfers to Elon Musk deepfake scam

Coinbase says it blocked $4.7 million in cryptocurrency transfers to scammers promoting a fake giveaway using an AI-generated deepfake of Elon Musk during a Tesla livestream that attracted more than 500,000 viewers.

Severity: Informational

Judge signs off on sale of Spirit Airlines’ data to Google

Google can take possession of defunct Spirit Airlines' data for $10 million, a federal bankruptcy judge has ruled. The tech giant agreed to protections as it plans to use the data in AI projects.

Severity: Informational

Lawmakers call on White House to develop defensive AI cyber systems

A bipartisan Senate duo urged the White House to launch a national effort to more robustly confront AI-enabled cyber threats in light of recent security incidents involving artificial intelligence.