1 个仓库
Using language models to evaluate the intent and context of code specifically for security vulnerability detection.
Distinct from LLM-Based Analysis: Focuses on security-specific intent and vulnerability detection rather than general code change interpretation.
Explore 1 awesome GitHub repository matching devops & infrastructure · Security Intent Analysis. Refine with filters or upvote what's useful.
SkillSpector 是一款安全扫描器,旨在在 AI 代理插件和扩展安装之前检测其中的漏洞和恶意模式。它作为一个运行时护栏,计算数值风险评分并分配严重性标签,以提供安装建议或阻止有风险的外部扩展。 该项目的独特之处在于使用语言模型执行语义代码分析,评估代码意图和上下文以减少误报。它还采用基于指纹的问题抑制技术,在重复扫描周期中跟踪并忽略已接受的风险。 该工具通过针对公共安全数据库的依赖项扫描来涵盖软件供应链安全,并支持从本地目录、远程 URL 和仓库进行多源资产摄取。它以多种机器可读和人类可读的格式提供漏洞报告,以便集成到 CI/CD 流水线中。
Uses large language models to evaluate code intent and context, reducing false positives in security detection.