Tom Eston interviews offensive AI researcher and PhD candidate Andrew Wilson, a former Bishop Fox partner who helped grow the firm from under 20 people to nearly 500, built award-winning AI solutions for SOC modernization, founded Cactus Con, and relocated his family to Guadalajara to open and scale a Bishop Fox office. They discuss Mexico’s […]
The post The Real State of Offensive Security: AI, Penetration Testing & The Road Ahead with Andrew Wilson appeared first on Shared Security Podcast.
The post The Real State of Offensive Security: AI, Penetration Testing & The Road Ahead with Andrew Wilson appeared first on Security Boulevard.
嘶吼安全动态
【国内新闻】
国家级电力AI中试基地启用，华为、百度入驻筑牢能源AI安全
摘要：作为电力人工智能领域的“桥梁型平台”，中试基地已成功连接100多家不同领域单位。
原文链接：https://baijiahao.baidu.com/s?id=1860252756515987591&wfr=spider&for=pc
中央网信办规范短视频标注，AI摆拍/虚假营销强制显形溯源
摘要：全平台整治无标识AI生成内容、虚构演绎，启用AI识别+人工复核，违规内容下架整改，净化内容生态。
原文链接：http://m.toutiao.com/group/7619651131685388815/
AI智能体风险被系统性揭示
摘要：国家互联网应急中心指出AI智能体面临提示词注入、插件投毒等风险，攻击者可诱导模型泄露敏感数据或执行恶意操作，攻击门槛显著降低。
原文链接：
https://www.stcn.com/article/detail/3691088.html
北京网安破获特大“网络开盒”案，涉案信息超千万条
摘要：嫌疑人搭建社工库非法售卖个人信息，涉案网站访问量30万+，5人因侵犯公民个人信息罪获刑1年6个月至7年，罚金1.5万-7万元。
原文链接：http://m.toutiao.com/group/7620051829627306534/
【国外新闻】
OpenClaw风险引发全球安全关注
摘要：AI智能体OpenClaw安全问题被认为具有全球影响，涉及设备劫持、数据泄露及金融操作风险，多国开始关注其潜在攻击面扩展问题。
原文链接：
https://www.chinanews.com.cn/sh/2026/03-23/10591104.shtml
OpenWebUI服务器遭攻击，被植入挖矿与信息窃取恶意代码
摘要：研究人员发现大量未开启认证的OpenWebUI实例被攻击，黑客利用其AI接口部署挖矿程序与信息窃取工具，并通过混淆技术隐藏恶意载荷，部分脚本疑似AI生成，显示AI应用正成为新型攻击入口。
原文链接：https://gbhackers.com/openwebui-servers-targeted/
Oracle修复高危RCE漏洞，可被远程未认证利用
摘要：Oracle修复CVE-2026-21992漏洞，影响Identity Manager与Web Services Manager。该漏洞无需认证即可远程执行代码，攻击者可完全控制系统、窃取身份数据并横向移动，CVSS评分高达9.8。
原文链接：https://gbhackers.com/oracle-fixes-high-severity-rce-vulnerability/
VoidStealer窃密木马绕过Chrome加密机制
摘要：新型信息窃取木马VoidStealer通过调试器技术绕过Chrome应用绑定加密（ABE），利用硬件断点在内存中提取主密钥，无需提权或注入代码，隐蔽性极强，标志浏览器安全防护再次被突破。
原文链接：
https://www.bleepingcomputer.com/news/security/voidstealer-malware-steals-chrome-master-key-via-debugger-trick/
Trivy漏洞扫描器遭供应链攻击，GitHub Actions被植入窃密程序
摘要：攻击者入侵Trivy项目并篡改GitHub Actions标签，将恶意代码注入CI/CD流程，窃取环境变量、密钥及云凭证。攻击利用标签投毒机制实现隐蔽传播，影响大量开发流水线。
原文链接：
https://www.bleepingcomputer.com/news/security/trivy-vulnerability-scanner-breach-pushed-infostealer-via-github-actions/
A threat actor has allegedly exfiltrated approximately 100 GB of personally identifiable information (PII) from Crunchyroll, the Sony-owned anime streaming giant, after gaining access through a compromised employee at the platform’s outsourcing partner, Telus. The breach, which reportedly occurred on March 12, 2026, has not been publicly acknowledged by Crunchyroll as of this writing. According […]
The post Crunchyroll Data Breach — Threat Actor Claims Exfiltration of 100 GB of User Data appeared first on Cyber Security News.