← 返回 Skills 市场
9667
总下载
8
收藏
0
当前安装
10
版本数
在 OpenClaw 中安装
/install safe-exec
功能描述
Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agen...
安全使用建议
Review this carefully before installing. It is local and I did not find hidden network exfiltration or background monitoring, but it should not be relied on as a safety boundary for agent command execution until approval, request validation, command parsing, and log-permission issues are fixed.
功能分析
Type: OpenClaw Skill
Name: safe-exec
Version: 0.3.4
The 'safe-exec' skill is presented as a security tool to intercept and require approval for dangerous shell commands executed by an AI agent. Its documentation (SKILL.md, READMEs, CLAWDHUB_SECURITY_RESPONSE.md) explicitly states no network calls, monitoring, or credential requirements, and the developer has actively removed previously problematic features. However, the core scripts (`scripts/safe-exec.sh` and `scripts/safe-exec-approve.sh`) use `eval "$COMMAND"` to execute commands. This is a critical shell injection vulnerability, as a sophisticated attacker could potentially bypass the risk assessment regexes or manipulate the command string to achieve arbitrary code execution, even for commands deemed 'low' risk or after user approval. Despite the clear intent to provide a security layer, this significant RCE risk makes the skill suspicious.
能力评估
Credentials
Local writes under ~/.openclaw are purpose-aligned, but pending request files and audit logs store full commands and sometimes user context without explicit restrictive permissions or redaction, which can expose secrets present in command lines.
Install Mechanism
Installation is disclosed as a GitHub clone with chmod and optional PATH symlinks; I found no install-time remote script pipe or hidden installer, though the skill places command wrappers in the user's PATH.
Instruction Scope
The skill discloses local command interception, audit logs, and agent mode, but the documentation's claim that approval protection is preserved is not supported by the scripts: non-interactive approval skips confirmation, and context text can downgrade commands.
Persistence & Privilege
There is no daemon or cron persistence in the inspected artifact, but persisted request files can be approved by unvalidated request IDs, and the approval utility can execute queued commands without an authenticated interactive approval channel.
Purpose & Capability
The stated purpose is to make agent shell execution safer, but the implementation executes caller-supplied command strings with eval, defaults unknown commands to low risk, and can automatically run medium/high commands when context contains confirmation phrases.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install safe-exec - 安装完成后，直接呼叫该 Skill 的名称或使用
/safe-exec触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v0.3.4
fix: 修复YAML metadata格式以符合ClawHub要求
v0.3.3
Security enhancement
v0.3.2
Add backward compatibility symlinks and improved documentation. Project restructuring with zero breaking changes - all existing users can upgrade without any modifications. New conversational installation method added.
v0.3.1
Remove markdown formatting from description, ensure English-only text
v0.3.0
Add quick install guide and GitHub issue link in description
v0.2.8
Clarify platform-agnostic design - works via in-session terminal notifications, independent of communication tools
v0.2.7
Fully English documentation with global enable mode (Enable SafeExec)
v0.2.6
Update usage to global enable mode (开启 SafeExec) instead of per-command execution
v0.2.5
Update documentation to English with conversational usage examples
v0.2.4
Fix non-interactive environment hang issue
元数据
常见问题
Safe Exec 是什么？
Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agen... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 9667 次。
如何安装 Safe Exec？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install safe-exec」即可一键安装，无需额外配置。
Safe Exec 是免费的吗？
是的，Safe Exec 完全免费（开源免费），可自由下载、安装和使用。
Safe Exec 支持哪些平台？
Safe Exec 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Safe Exec？
由 OTTTTTO（@ottttto）开发并维护，当前版本 v0.3.4。
推荐 Skills