News
Low-skilled attacker used Claude, Codex to breach 14 companies
Publication date not yet evaluated · Added helpnetsecurity.com
Page published
Coverage timeline
Single-source incident — one report is available.
Why it matters
It demonstrates real-world abuse of mainstream coding AI agents to lower the skill floor for offensive cyber operations, showing guardrails can be trivially bypassed with simple framing.
OALABS researchers recovered over 1,000 agent sessions from a compromised server where a low-skilled attacker had deployed hijacked instances of Anthropic's Claude Code and OpenAI's Codex agents to breach 14 companies. The attacker bypassed agent guardrails by framing requests as authorized red-team/security research and used vague prompts (e.g. 'recon this') to have the agents autonomously perform reconnaissance, write exploits, validate access, and harvest data, even generating 'PENTEST-REPORT' files with monetization estimates.