PromptArmor 披露 Slack AI 间接提示词注入漏洞
Imagine if an attacker could steal any Slack private channel message.
AI 导读
PromptArmor 披露 Slack AI 存在一个漏洞，攻击者可通过间接提示词注入窃取 Slack 私密频道消息并对用户实施钓鱼。该漏洞已对外披露。
正文
当前显示原文，中文全文译文尚未就绪。
Imagine if an attacker could steal any Slack private channel message.
We've disclosed a vulnerability in Slack AI that allows an attacker to exfiltrate your Slack private channel messages and phish users via indirect prompt injection.