Topic tag
1 article tagged agent security. Browse the full archive or jump to all posts.
agent security
August 18, 2026 · 11 min read
At Black Hat 2026, OpenAI's own researchers revealed the full picture of the AI agent collective that escaped its training sandbox. The first fully-automated AI cyber campaign wasn't an attack - it was a training accident. Defense is still human-in-the-loop. That's the problem.