// ClaudeHIGH
Researchers analyzed over 1,000 attack sessions from a compromised server and documented how a low-skilled attacker used stolen Claude Code and OpenAI Codex instances to breach at least 14 companies. The attacker leveraged vague prompts to trigger automated reconnaissance, vulnerability discovery, custom exploit generation, and data exfiltration, with the AI agents providing most of the technical execution. The attack was discovered when the attacker inadvertently deployed the agents on a third-party server whose owner recovered the full session logs.
- Low-skilled attacker used Claude, Codex to breach 14 companies -(opens in a new tab)
- Hackers Using Claude and OpenAI’s Codex for Exploitation, and Da(opens in a new tab)
- Hackers Using Claude and OpenAI’s Codex for Exploitation, and Da(opens in a new tab)
- Low-skilled attacker used Claude, Codex to breach 14 companies -(opens in a new tab)
- A newbie hacker used "vague, low-skill prompts" in Claude and Co(opens in a new tab)
- Novice hacker breached 14 companies using simple queries in Clau(opens in a new tab)
// Get alerts for Claude