开源 LLM 工程平台：追踪、评测、提示词管理与指标。
SkillSpector (NVIDIA)
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.
- Репозиторий
- NVIDIA/SkillSpector
- Звёзды
- ★ 20 504
- Форки
- 1 805
- Язык
- Python
- Лицензия
- Apache-2.0
- Последнее обновление
- 2026-10-17
- Переходы
- 0
MCP
Похожие проекты
测试提示词、模型与 RAG 的评测与红队工具，CLI 与 CI 友好。
大模型少样本评测框架，Open LLM Leaderboard 背后的工具。
Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.
用众多可复用的提示词模式增强人类能力的开源框架。
An AI prompt optimizer for writing better prompts and getting better AI results.