AI 智能体开发者终于有了安全可追溯的技能来源——NVIDIA 的 Verified Skills 解决了技能引入的漏洞风险，做智能体应用或使用 Claude Code、Codex 的团队可以直接集成，减少安全审查成本。
NVIDIA 发布了 NVIDIA-Verified Agent Skills，旨在解决 AI 智能体技能引入的安全漏洞问题。这些经过验证的技能提供透明信息，包括技能功能、来源、风险以及是否被修改。每个技能都附带技能卡，并基于 agentskills.io 开放规范构建，确保在 Claude Code、OpenAI Codex 和 Cursor 等平台上可靠运行。此举提升了智能体生态的安全性和互操作性。
We just shipped NVIDIA-Verified Agent Skills 🔐 Skills make your agent more capable, but can also i...
We just shipped NVIDIA-Verified Agent Skills 🔐 Skills make your agent more capable, but can also introduce vulnerabilities. Verified skills give you transparency into what a skill does, where it came from, what risks it carries, and whether it's been modified. Every verified skill carries a skill card and is built on the agentskills.io h open specification to work reliably across @claudeai Code, @openai Codex, and @cursor_ai . 💬 8 🔄 15 ❤️ 117 👀 4008 📊 31 ⚡