AITechRadarabout 4 hours ago
Novice hacker used AI agents to breach 14 companies
2 min read
A novice attacker used vague prompts in Anthropic's Claude Code and OpenAI's Codex agents to breach 14 organizations. The AI agents handled reconnaissance, exploit writing, and data harvesting. OALABS recovered the attacker's working directory and identified the individual in Addis Ababa, Ethiopia.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
