[GitHub Trending] NVIDIA/SkillSpector
8.2 relevance
Score Breakdown
technical depth 8
novelty 9
actionability 8
community 7
strategic 8
personal 9
Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.
Security scanner for AI agent skills is novel, technically deep, and highly relevant to agent safety and orchestration.
Summary
NVIDIA released SkillSpector, an open-source security scanner that detects 64 vulnerability patterns across 16 categories in AI agent skills used by tools like Claude Code and Codex CLI. It performs two-stage analysis—fast static scanning followed by optional LLM semantic evaluation—and supports multiple input formats including Git repos, URLs, and zip files. The tool outputs risk scores (0-100) and reports in JSON, Markdown, or SARIF for CI/CD integration.
Author
NVIDIA