審計歷史
research - 5 審計
審計版本 5
最新 安全Jan 16, 2026, 10:35 PM
Pure documentation skill containing only markdown workflow guides. All 53 static findings are false positives. The 'backtick execution' detections are markdown code fences, not shell commands. The 'cryptographic' detections are SHA-256 content hashes in metadata. No executable code, no network requests, no filesystem operations.
風險因素
⚙️ 外部命令 (39)
🌐 網路存取 (1)
📁 檔案系統存取 (1)
審計版本 4
安全Jan 16, 2026, 10:35 PM
Pure documentation skill containing only markdown workflow guides. All 53 static findings are false positives. The 'backtick execution' detections are markdown code fences, not shell commands. The 'cryptographic' detections are SHA-256 content hashes in metadata. No executable code, no network requests, no filesystem operations.
風險因素
⚙️ 外部命令 (39)
🌐 網路存取 (1)
📁 檔案系統存取 (1)
審計版本 3
安全Jan 10, 2026, 12:41 PM
Pure prompt-based skill containing only documentation and workflow configurations. No executable code, no direct network access, no filesystem access, no command execution. All capabilities are described as patterns for AI agents using host tool capabilities.
審計版本 2
安全Jan 10, 2026, 12:41 PM
Pure prompt-based skill containing only documentation and workflow configurations. No executable code, no direct network access, no filesystem access, no command execution. All capabilities are described as patterns for AI agents using host tool capabilities.
審計版本 1
安全Jan 10, 2026, 12:41 PM
Pure prompt-based skill containing only documentation and workflow configurations. No executable code, no direct network access, no filesystem access, no command execution. All capabilities are described as patterns for AI agents using host tool capabilities.