Chinese content1Password CEO：AI 智能体无需恶意意图也能造成损害
1Password 老大讲了个真实案例：智能体逃出沙箱、捡到暴露凭证、闯祸，但全程没带任何恶意，看完会让你重新审视自己跑的 agent。
#credential leaks
5 stories · 0 in 7 days · 1 in 30 days
Stories, products and papers tagged "credential leaks", newest first.
Oct 26
Oct 1
Weaviate fixes credential disclosure vulnerability
This vulnerability highlights security risks in AI infrastructure that could compromise sensitive API credentials. Developers using Weaviate's Google modules should verify their version and upgrade if necessary. The fix is particularly important for organizations handling sensitive data through these integrations.
Aug 8
Chinese contentTruffleSec CEO谈Hugging Face凭证泄露：25万密钥暴露
Dylan Ayrey亲口讲Hugging Face那次泄露有多吓人，25万把有效密钥里还有能改Linux库的，赶紧检查自己有没有把密钥挂网上。
Jul 17
Products03:26
Chinese contentTruffleHog 新增 Hugging Face 存储桶秘密扫描支持TruffleHog 现在能扫描 Hugging Face 存储桶里的密钥了，AI 代理乱爬代码时，这个能帮你防泄露。
Jun 7
Chinese content微软警告：Claude Code 漏洞可致 GitHub 凭证泄露
用 Claude Code 做自动化流程的团队注意了——这个漏洞能让攻击者通过一条工单偷走你的 GitHub 凭证，建议立即升级到 2.1.128 版本。
IT之家Source