← Back to Skills Marketplace
9666
Downloads
8
Stars
0
Active Installs
10
Versions
Install in OpenClaw
/install safe-exec
Description
Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agen...
Usage Guidance
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.
Capability Analysis
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.
Capability Assessment
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.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install safe-exec - After installation, invoke the skill by name or use
/safe-exec - Provide required inputs per the skill's parameter spec and get structured output
Version History
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
Metadata
Frequently Asked Questions
What is Safe Exec?
Safe command execution for OpenClaw Agents with automatic danger pattern detection, risk assessment, user approval workflow, and audit logging. Use when agen... It is an AI Agent Skill for Claude Code / OpenClaw, with 9666 downloads so far.
How do I install Safe Exec?
Run "/install safe-exec" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Safe Exec free?
Yes, Safe Exec is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Safe Exec support?
Safe Exec is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Safe Exec?
It is built and maintained by OTTTTTO (@ottttto); the current version is v0.3.4.
More Skills