2026年全代理构建时代，如何有效防止密钥泄入Git？HN网友分享一线安全最佳实践与工具。
Hi HN friends, it's july 2026 and I am assuming many of you use fully agentic building now. Securing secrets and credentials from being committed to G…
首个金融多模态越狱检测数据集FENCE，揭示VLM脆弱性并填补资源空白。
arXiv:2602.18154v2 Announce Type: replace-cross Abstract: Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and …
npm 12大版本即将到来，安全相关默认变更需提前适配，现在即可通过警告预览调整。
Article URL: https://github.blog/changelog/2026-06-09-upcoming-breaking-changes-for-npm-v12/ Comments URL: https://news.ycombinator.com/item?id=484677…
Progent 开创性地将权限控制引入 AI 代理安全，用符号规则定义最小权限策略，并通过 LLM 动态生成更新、SMT 求解器确保单调限制——权限只能缩窄不能随意扩大。这从根本上解决了自主代理面临间接注入攻击时安全与效用冲突的难题，堪称 LLM 安全治理的标杆方案。
arXiv:2504.11703v3 Announce Type: replace-cross Abstract: AI agents interact with external environments through tool calls, exposing them to attacks l…