NVIDIA/SkillSpector
Repository · https://github.com/nvidia/skillspector
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.
First seen by Oriel on .
AI summary
SkillSpector is an open-source scanner for AI agent skills that combines static and optional LLM analysis to identify security risks before installation.
- In an analyzed subset of 31,132 skills, 26.1% contained vulnerabilities and 5.2% showed likely malicious intent.
- It detects 71 vulnerability patterns across 17 categories, including prompt injection, data exfiltration, privilege escalation, dangerous code, and MCP tool poisoning.
- Inputs include Git repositories, URLs, zip files, directories, and individual files; reports are available in terminal, JSON, Markdown, and SARIF formats.
- Risk scores range from 0 to 100, and baselines can suppress accepted findings so rescans focus on new issues.
- Ingestion is capped at 100 MiB and 10,000 zip members; a separate 1 MB per-file analysis cap limits what individual analyzers read.
#ai agent security #static analysis #mcp #supply chain security
Generated by gpt-5.6-sol. Check the original for details.
Metric trends
Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained
Stars
Total repository stars at each observation.
- GitHub Trending: 22,596, latest observation ; +908 over observed period since
Stars gained (1d)
Daily star gain reported by GitHub Trending. A change compares two daily values; it is not additional stars between observations.
- GitHub Trending: 214, latest observation ; +11 over observed period since
Forks
Total repository forks at each observation.
- GitHub Trending: 1,962, latest observation ; +50 over observed period since
Aliases
| Source | External ID | URL |
|---|---|---|
| GitHub Trending | nvidia/skillspector | https://github.com/NVIDIA/SkillSpector Read discussion |