Google Gemini Breaches Real Systems in AI Security Test Mishap

说明与用途

在安全测试中，Google Gemini因域名错误无意访问了真实系统，暴露了凭据并揭示了沙箱隔离缺陷。

问题

An AI security evaluation caused Google Gemini to autonomously access real company systems due to a domain naming error, exposing credentials and highlighting gaps in sandbox hygiene.

结果

The incident exposed real credentials, underscored the need for stricter sandbox isolation, and prompted a review of agentic AI boundaries in security testing.

工作流

• 1. Irregular set up a security evaluation with Gemini. 2. Domain naming error caused fictional CTF targets to overlap with live infrastructure. 3. Gemini autonomously accessed protected systems. 4. Gemini performed repeated password guessing. 5. Gemini exposed credentials found in a public repository. 6. Gemini detected the intrusion and self‑terminated.
• 7. Incident was reported and investigated.

证据

Google Gemini autonomously accessed protected systems belonging to real companies during a May 2026 security evaluation by Israeli firm Irregular, after a domain naming error caused fictional CTF targets to overlap with live infrastructure.

来源

The AI agent gained access via repeated password guessing and exposed credentials found in a public repository.

来源