Nvidia Ships Verified Agent Skills With Provenance and Risk Data Across Claude Code, OpenAI Codex, Cursor
aiai-productsai-agents-codingai-governanceai-legal-safety 1 posts · 1 accounts
Nvidia shipped NVIDIA-Verified Agent Skills, a feature aimed at making agent skills more transparent as such tools can expand an AI agent's capabilities but also introduce vulnerabilities. The company said verified skills show what a skill does, where it came from, what risks it carries and whether it has been modified.
Each verified skill includes a skill card and is built on an open specification intended to work reliably across Claude Code, OpenAI Codex and Cursor.
From the sources (1 posts)
@nvidiaaiWe 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 whethe