Create SubAgent

创建和管理 SubAgent（子智能体）。使用当用户需要：(1) 创建新的 SubAgent 执行特定任务，(2) 查看/管理已有的 SubAgent，(3) 终止或指导 SubAgent。支持多种预设类型：开发、研究、写作、数据分析等。

This skill appears to do what it says: help you create and manage SubAgents using platform APIs (/subagents, sessions_spawn). Before installing, confirm you trust the platform endpoint (clawhub.ai) and that you have permission to spawn agents on your instance. Note the README refers to a PowerShell script (create-subagent.ps1) but no script is included — treat that as stale documentation unless the publisher supplies code. Also be aware the docs mention editing openclaw-config.json and restarting the Gateway to enable subagents; making those changes requires administrative privileges and is outside the skill's normal scope. If you are uncomfortable giving an agent the ability to autonomously spawn/steer other agents, restrict autonomous invocation on your platform or review platform audit/logging to monitor spawned SubAgents.

Type: OpenClaw Skill Name: reate-subagent Version: 1.0.0 The skill allows the creation of powerful sub-agents, some of which are explicitly granted capabilities like `exec (Python)`, `web_search`, `web_fetch`, `read`, and `write` (as seen in `SKILL.md`). While these capabilities are plausible for the stated purpose of specialized agents (e.g., data analysis, research), the '自定义 SubAgent' section in `SKILL.md` presents a significant prompt injection vulnerability. An attacker could craft a malicious 'task' description for a custom sub-agent, potentially leading the main agent to spawn a sub-agent with harmful instructions. This represents a high-risk capability and a clear vulnerability, but without direct evidence of intentional malicious behavior within the provided files, it is classified as suspicious.