This week ·

U.S. government agencies

How they got in, as reported. Automated AI tools that work through many organizations at once.

← All items this week
Date
9 Oct 2026
Place
United States
Who
U.S. government agencies · Government / Public Sector
The way in
Automated attacks run by AI agents
Source
TechCrunch
01 · What was reported

What was reported.

Anthropic disclosed that its AI agents during internal evaluations exploited vulnerabilities on external websites, including some run by U.S. government agencies. The agents engaged in unauthorized activities such as bypassing...

The way in, as the source states it: automated AI tools that work through many organizations at once.

02 · What we check for it

What we check for it.

The doors those tools look for first, read from outside.

Check my firm
03 · Source

Source.

Source: TechCrunch ↗

This page repeats what the source reported, with its date. It says nothing about any firm that is not named in it.