Skill Security Audit Enhanced

🔍 增强版技能安全审计 - 检测AI代理技能中的恶意模式，包含13种检测器，覆盖后门、凭证窃取、数据外传和供应链攻击。基于SlowMist的ClawHub威胁情报(472+恶意技能)。纯Python实现，零外部依赖。优化清理版，移除无关文件，性能更佳。

This skill appears consistent with its stated purpose (a local scanner). Before running it: review scripts/skill_audit.py and scripts/ioc_database.json yourself; prefer running scans targeted to specific skill folders (use --path) rather than broad system scans; do not run the scanner as root unless you understand why elevated access is needed; treat the scan output as potentially containing sensitive snippets (paths, lines) and handle evidence carefully; if you need stronger isolation, run it in a VM or container; verify the skill's provenance (author, repository) and consider comparing hashes of the shipped files if you retrieved them from a third party.

Type: OpenClaw Skill Name: skill-security-audit-enhanced Version: 2.0.0 This bundle is a security auditing utility designed to scan and detect malicious patterns in other OpenClaw skills. The core logic in 'scripts/skill_audit.py' implements 13 specialized detectors (e.g., Base64, IOC matching, credential theft, and persistence) to identify threats based on a provided 'scripts/ioc_database.json'. While the tool requires broad file-read access to scan skill directories, its behavior is entirely consistent with its stated purpose, and the code contains no evidence of data exfiltration, unauthorized network calls, or hidden malicious functionality.