Skip to content

[GitHub Trending] NVIDIA/SkillSpector

8 relevance
Score Breakdown
technical depth
8
novelty
9
actionability
7
community
7
strategic
8
personal
9

Scored daily by a customisable AI persona to surface the most relevant engineering leadership news.

Directly relevant to AI agent security, a critical emerging concern for the reader's focus on agent orchestration.

AI/ML github.com
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks. - NVIDIA/SkillSpector
Summary

NVIDIA released SkillSpector, an open-source security scanner for AI agent skills that detects 64 vulnerability patterns across 16 categories including prompt injection, data exfiltration, and supply chain risks. It supports multi-format input (Git repos, URLs, zip files, directories) and offers two-stage analysis with fast static scanning plus optional LLM semantic evaluation. The tool outputs risk scores (0-100) and reports in terminal, JSON, Markdown, or SARIF formats, with live CVE lookups via OSV.dev and offline fallback.

Author

NVIDIA