Multi-Agent Coordinator

Production-ready multi-agent orchestration system for OpenClaw. Implements Coordinator Mode with real parallel worker spawning via sessions_spawn, XML task n...

This skill is functionally coherent with a multi-agent orchestrator, but take precautions before running it: - Expect to need the OpenClaw CLI (or equivalent) in PATH: the scripts call subprocess commands like 'openclaw sessions spawn' though the registry metadata claims no required binaries; install and verify the OpenClaw CLI you plan to use first. - The SKILL.md and code are inconsistent about spawn commands (SKILL.md shows 'sessions_spawn' while code uses 'openclaw sessions spawn'); verify the correct invocation for your environment. - Spawned workers are explicitly allowed to run file operations, shell commands, and web fetches and are instructed to include concrete file paths and code snippets in outputs — run this skill only in an isolated/sandbox workspace without secrets or sensitive files. - Review the worker prompt templates and scripts (coordinator_v2.py, coordinator_phase2.py, worker.py) to confirm they do not exfiltrate data to external endpoints you don’t control. The package itself does not contain external network endpoints, but worker prompts could instruct sub-agents to perform web requests. - Test in a disposable environment first (empty repo, no credentials), and inspect .openclaw/scratchpad after runs. If you need to use in production, consider adding explicit restrictions/sandboxing on spawned workers and ensure the OpenClaw CLI you trust is used. If you want, I can list the exact lines where subprocess calls are made and point out the files/sections that should be reviewed or edited before use.

Type: OpenClaw Skill Name: multi-agent Version: 0.1.0 The skill bundle implements a multi-agent orchestration system that allows a coordinator agent to spawn and manage worker agents. The system includes scripts (scripts/worker.py, scripts/coordinator_phase2.py) that utilize subprocess.run with shell=True to execute arbitrary bash commands and OpenClaw CLI tools. While these high-risk capabilities are aligned with the stated purpose of a parallel execution framework, the lack of input sanitization and the inherent risks of shell execution make the bundle vulnerable to command injection. No evidence of intentional malice, such as data exfiltration or unauthorized persistence, was found.