审计历史
creating-agents - 6 审计
审计版本 6
最新 安全Jan 21, 2026, 03:32 PM
All detected patterns are false positives. The skill contains only documentation and templates for creating Claude Code agents. Backticks in markdown files are for code examples, not execution. Hidden file references are legitimate agent storage locations. No actual security risks identified.
审计版本 5
中风险Jan 16, 2026, 07:11 PM
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
风险因素
⚙️ 外部命令 (70)
📁 文件系统访问 (6)
🌐 网络访问 (1)
检测到的模式
审计版本 4
中风险Jan 16, 2026, 07:11 PM
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
风险因素
⚙️ 外部命令 (70)
📁 文件系统访问 (6)
🌐 网络访问 (1)
检测到的模式
审计版本 3
安全Jan 10, 2026, 11:32 AM
Pure documentation skill containing only Markdown files with agent configuration guidance. No executable code, scripts, network calls, or file system access beyond its own files. This is a prompt-based skill for educational purposes.
审计版本 2
安全Jan 10, 2026, 11:32 AM
Pure documentation skill containing only Markdown files with agent configuration guidance. No executable code, scripts, network calls, or file system access beyond its own files. This is a prompt-based skill for educational purposes.
审计版本 1
安全Jan 10, 2026, 11:32 AM
Pure documentation skill containing only Markdown files with agent configuration guidance. No executable code, scripts, network calls, or file system access beyond its own files. This is a prompt-based skill for educational purposes.