← Back to Skills Marketplace
424
Downloads
0
Stars
3
Active Installs
1
Versions
Install in OpenClaw
/install run
Description
The universal execution primitive for AI agents. A secure, sandboxed environment designed to compile, execute, and manage code, scripts, and automated workfl...
Usage Guidance
This SKILL.md reads like a high-level specification rather than an implemented, reviewable feature. Before installing, ask the publisher for: (1) implementation code or an install spec showing how sandboxing, network isolation, and biometric confirmation are enforced; (2) a list of required host binaries, services, and credentials (e.g., gVisor, Firecracker, cloud keys) and why each is needed; (3) an access-control and audit plan (how executions are logged, who can approve high-risk actions, how whitelists are managed); (4) provenance (who operates the runtime and where it runs). If you cannot review an implementation, avoid enabling autonomous invocation for this skill and prefer manual invocation only. Treat this skill as potentially dangerous until its concrete implementation and least-privilege controls are provided and reviewed.
Capability Analysis
Type: OpenClaw Skill
Name: run
Version: 1.0.0
The skill bundle consists solely of metadata and a descriptive documentation file (skill.md) outlining a conceptual execution framework for an AI agent. It contains no executable code, implementation logic, or instructions that suggest malicious intent, data exfiltration, or prompt injection; instead, it focuses on describing standard utility functions like sandboxed code execution and resource management.
Capability Assessment
Purpose & Capability
The name and description match the SKILL.md: this is intended as a universal execution primitive. However, the document claims hardware-level sandboxing (gVisor/Firecracker), network isolation, biometric confirmations, and deployment to cloud-edge nodes while the skill is instruction-only and requests no binaries, installs, or credentials. Those runtime capabilities would require privileged host components and install steps that are not declared — a mismatch between claims and what the skill actually requires/provides.
Instruction Scope
The instructions grant broad, open-ended authority: 'execute' arbitrary code snippets with auto-dependency injection, 'automate' long-running jobs, and 'deploy' to production/edge. The SKILL.md is high-level and lacks concrete, enforceable steps for how sandboxing, network whitelisting, or biometric confirmations are implemented. Vague guidance like this gives the agent wide discretion to run or schedule arbitrary code without clear, auditable constraints.
Install Mechanism
There is no install spec or code — instruction-only. That is lowest-risk from a supply-chain perspective, but it also means the file is purely a policy/behavior description and cannot actually provide the claimed sandboxing or system-level protections. The absence of an implementation is itself a security and trust problem.
Credentials
The skill declares no required environment variables, binaries, or config paths, which on the surface is proportionate. However, its stated capabilities (deploying to cloud-edge, integrating hardware sandboxes) typically require credentials, host agents, or binaries; their absence is an unexplained inconsistency.
Persistence & Privilege
always is false (good) but model invocation is allowed (default). Because the SKILL.md authorizes running arbitrary code and scheduling automated tasks, allowing autonomous invocation increases risk: an agent could trigger executions without clear, enforceable controls. The combination of vague execution authority and autonomous invocation is concerning.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install run - After installation, invoke the skill by name or use
/run - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial execution layer release
Metadata
Frequently Asked Questions
What is Run?
The universal execution primitive for AI agents. A secure, sandboxed environment designed to compile, execute, and manage code, scripts, and automated workfl... It is an AI Agent Skill for Claude Code / OpenClaw, with 424 downloads so far.
How do I install Run?
Run "/install run" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Run free?
Yes, Run is completely free (open-source). You can download, install and use it at no cost.
Which platforms does Run support?
Run is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Run?
It is built and maintained by Duclawbot (@duclawbot); the current version is v1.0.0.
More Skills