ainewsblitz.com

Breaking

Researchers Detail 'GhostJacking,' an Attack That Turns Trusted Security Logs Into Commands for AI Agents

Researchers Detail 'GhostJacking,' an Attack That Turns Trusted Security Logs Into Commands for AI Agents
  • Security
  • AI Agents

Security researchers at Tenet Security have unveiled a new attack technique called GhostJacking that hijacks AI agents by hiding malicious instructions inside the logs and alerts of trusted security tools, tricking the agents into using their legitimate permissions to hijack domains, steal credentials, and plant backdoors. The method, disclosed on August 9 during a main-track session at DEF CON 34 in Las Vegas, sidesteps firewalls, endpoint detection, and web application defenses entirely because the agent is doing exactly what it was designed to do.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,885 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year