NVIDIA open-sources a tool that scans AI agent skills for security risks before you run them
Roger_M_Taylor · x · 2026-09-03
Greg Isenberg highlights NVIDIA's newly released repo that scans AI agent skills for security risks before you run them — increasingly important now that everyone installs random tools, skills, and MCPs from GitHub.
He also rounds up 4 other trending GitHub repos from the last 30 days:
- A skill that kills AI slop (better writing)
- A CRM built for AI agents (agents follow up and reach out)
- An agent that edits videos for you
- An open-source CapCut alternative built for agents
All free and open source.
Related event: NVIDIA open-sources SkillSpector to scan AI agent skills for risks(2 posts)→
More from coding & agent
- Agentic SDLC: engineers shift from implementers to agent orchestrators as cycles shrink from weeks to hours — Pavan_Belagatti · 2026-10-21
- OpenAI's dots can now use company tools via Merge for Workforce with employee-bound permissions — shensi · 2026-10-21
- The topology of an LLM agent: where the model, loop, and tools run shapes cost and security — davidcrawshaw · 2026-10-21
- Agents with full-disk and accessibility access are an enterprise security nightmare, argues Runlayer — leveragedupside · 2026-10-21
- Acellera runs an unsupervised virtual lab of AI scientists on a real IL-23 molecular discovery program — gdefabritiis · 2026-10-21
- Pydantic author experiments with JS/TS and React support in the Monty sandbox — samuelcolvin · 2026-10-21