@torchesfrms

skill-sec-scan provides static rule-based detection of security threats across multiple languages, supplemented by optional llm semantic analysis to reduce false positives. covers 57 rules across four threat categories with 100-point risk scoring.

Monitors Twitter daily at 16:00 to find and filter new AI Agent, Crypto, and DeFi projects matching specific keywords, outputting raw and curated data.

自动检测 JavaScript、TypeScript、Python 和 Shell 文件中的数据外泄、注入、代码混淆与木马后门等安全风险并生成详细报告。