安全文件编辑器

安全文件编辑器，支持4眼原则预览确认，原子备份与回滚，避免误操作覆盖及注入风险，保障文件编辑安全可靠。

This skill appears to implement what it claims: preview-only edits, atomic backup, commit, and rollback, with no network calls or credentials required. Before installing or using it: 1) Review or change the backup/log directory to a location you control (the code uses ~/.openclaw/... by default; SKILL.md documents a different default), and ensure those files have restricted permissions because logs and backups can contain sensitive content. 2) Test on non-production files to confirm behavior (the diff is a simple replacement summary, not a full diff). 3) Be aware the tool can modify any file the running agent/user has permission to write — grant access only where appropriate. 4) Consider fixing small robustness issues (e.g., potential undefined backup_path on certain exceptions) before trusting it in critical environments.

Type: OpenClaw Skill Name: safe-file-editor Version: 1.0.0 The 'safe-file-editor' skill is designed to enhance security during file modifications by implementing a '4-eye principle' (preview before execution), atomic writes, and automatic backups. The implementation in safe_file_editor.py follows these safety protocols using standard Python libraries, and the SKILL.md instructions explicitly guide the AI agent to require user confirmation and perform dry runs, with no evidence of data exfiltration or malicious execution.