AI 导读
Fabraix 推出了 Nyx，一款全新的自主红队智能体！ 用户可以将它指向任何 AI 智能体，从包含 10,000+ 越狱攻击的库中运行对抗性攻击，以发现安全漏洞。 > 每一项发现都会向智能体输出攻击步骤，使其能够识别漏洞。 > 同一测试可在发布后重放，以检查漏洞是否已修复。 语音 AI 渗透测试示例 🤖
正文
Fabraix has launched Nyx, a new autonomous red-teaming agent!
Users can point it at any AI agent and run adversarial attacks from a library of 10,000+ jailbreaks to surface security holes.
> Every finding outputs the attack steps to the agent so it can spot a vulnerability.
> The same test can be replayed after a release to check if it was fixed.
Voice AI pentesting sample 🤖
来源：@testingcatalog · x.com