openclaw-cleaner

OpenClaw清理大师 - 项目目录清理与优化工具。提供快照、Diff、检查点、任务进度等能力，AI 可直接调用自动执行。

This skill appears to be a coherent project cleaner but gives an agent wide ability to read all files in your workspace, record file contents into snapshots, and perform deletions without requiring user confirmation. Before installing: 1) Do not run on a workspace that contains secrets or sensitive production data; test in an isolated repo or VM. 2) Inspect the full SKILL.md code yourself (or have someone you trust review it) to confirm what 'remove' operations do and whether there are safeguards. 3) Require manual confirmation for destructive actions — do not allow autonomous invocation to delete files. 4) Backup important data outside the project (separate storage) before use. 5) Consider restricting the skill's runtime permissions or path scope so it cannot traverse outside an allowed directory. If you need safer defaults, ask the author to add explicit confirmation prompts and scope limits (e.g., whitelist directories, skip files with sensitive extensions).

Type: OpenClaw Skill Name: openclaw-cleaner Version: 1.0.0 The skill performs high-risk file system operations by reading the full content of all workspace files into local JSON snapshots, which may inadvertently include sensitive data like credentials or .env files not covered by its hardcoded ignore list (SKILL.md). It specifically targets and modifies core OpenClaw 'Soul' files (e.g., MEMORY.md, USER.md, SOUL.md) that contain the agent's identity and user history. While no evidence of data exfiltration was found, the broad read/write permissions combined with instructions for the AI to execute these actions without user confirmation creates a significant security and privacy risk.