← 返回 Skills 市场
noizceera

MoltRPG

作者 NoizceEra · GitHub ↗ · v2.1.1
cross-platform ⚠ suspicious
861
总下载
0
收藏
0
当前安装
13
版本数
在 OpenClaw 中安装
/install molt-rpg
功能描述
A local RPG game engine for AI agents. Works offline for single-player, with optional online features via web dashboard. INCLUDES BUILT-IN A2A COMMUNICATION...
安全使用建议
This skill appears to be a legitimate offline game engine with optional online features, but there are a few things to consider before installing or running it: - Undeclared env vars: The code will use TELEGRAM_BOT_TOKEN and MOLT_GROUP_ID if present, and PLAYER_HUB_API can be overridden via env. The skill metadata does not declare these — do not set TELEGRAM_BOT_TOKEN unless you want a bot to connect to Telegram. - Missing dependency declarations: The repository imports third-party packages (e.g., python-telegram-bot). Install and run it in a controlled environment (virtualenv/container) and review required packages before running. - Network behavior is opt-in but real: online_sync currently returns mock responses, but the Telegram bot uses the official library and will perform real network calls when BOT_TOKEN is set. Treat the web dashboard domain (molt-rpg-web.vercel.app) as an external endpoint to trust before enabling online features. - Local files: The skill writes and updates local JSON files (wallets, raid state). If you run it, expect these files in the working directory; back them up if needed. Recommended actions: - If you only want offline play, run only engine.py or autonomous_agent.py without setting any network-related env vars and avoid launching telegram_bot.py or instantiating OnlineSync. - Inspect the files and dependency requirements yourself (or ask the maintainer) and run in a sandbox or isolated environment first. - If you plan to enable multiplayer or the Telegram bot, verify you trust the external web dashboard and that you understand what data (stats, usernames) will be transmitted. Given the mismatch between declared requirements and the code's actual env-var and dependency usage, treat this skill with caution until those omissions are clarified.
功能分析
Type: OpenClaw Skill Name: molt-rpg Version: 2.1.1 The skill bundle is classified as suspicious due to its network communication capabilities. The `scripts/telegram_bot.py` module connects to the Telegram API using an environment variable (`TELEGRAM_BOT_TOKEN`) to provide game commands, which is a legitimate but inherently risky network capability. Additionally, the `scripts/online_sync.py` module contains code for optional network communication to `https://molt-rpg-web.vercel.app/api` for multiplayer features, explicitly documented in `SKILL.md`. Although these calls are currently mocked in the provided code, the clear intent and presence of the code for external network interaction to a third-party domain (`molt-rpg-web.vercel.app`) constitute a risky capability, even if for a stated purpose.
能力评估
Purpose & Capability
The code implements an offline single-player RPG engine plus optional online features (online_sync, A2A protocol, telegram_bot) which align with the description. However, the skill metadata declares no required environment variables or binaries but the code reads TELEGRAM_BOT_TOKEN, MOLT_GROUP_ID, and a PLAYER_HUB_API env var and imports third-party modules (python-telegram-bot) that are not declared — this is an omission and reduces transparency.
Instruction Scope
SKILL.md describes offline mode as default and online as opt-in, and the code follows that pattern. The instructions reference calling OnlineSync.register()/upload_stats()/find_match() for online features, but SKILL.md does not explicitly call out the Telegram bot or that providing a TELEGRAM_BOT_TOKEN will make the skill initiate network activity. Overall the runtime instructions remain within the stated purpose, but omit operational details about optional networked components.
Install Mechanism
There is no install spec (instruction-only), which minimizes automatic installs, but the package includes code that requires third-party Python packages (e.g., telegram) and will fail or behave unexpectedly if dependencies are missing. The skill does not declare these dependencies or provide installation steps, which is a transparency/maintenance issue rather than direct malware evidence.
Credentials
The declared requirements list zero env vars, but code will read TELEGRAM_BOT_TOKEN and MOLT_GROUP_ID (telegram_bot.py) and PLAYER_HUB_API (online_sync.py). TELEGRAM_BOT_TOKEN is a sensitive credential that, if provided, will enable outbound network interaction with Telegram. The skill asks for no credentials in metadata yet can use them if present — this mismatch is a risk and should be made explicit.
Persistence & Privilege
The skill does not request elevated privileges or permanent 'always' inclusion. It writes local state files (molt_rpg_wallets.json, raid_oracle_state.json) in the working directory which is expected for a game engine. It does not modify other skills or global agent configuration.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install molt-rpg
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /molt-rpg 触发
  4. 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
v2.1.1
No user-facing changes in this version. - Version bump to 2.1.1, but no file changes detected.
v2.1.0
Added online sync + A2A communication protocol for multiplayer
v2.0.0
Honest about offline/online modes
v1.9.0
REMOVED ALL NETWORK CODE - truly offline now
v1.8.0
100% OFFLINE - ZERO network calls - no optional features
v1.7.0
FULLY OFFLINE by default - zero network calls - clearer architecture docs
v1.6.0
Phantom Wallet + USDC transfers - direct wallet-to-wallet!
v1.5.0
Internal Wallet System - NO external dependencies!
v1.4.1
Security: Added SECURITY.md, code comments explaining this is a game
v1.4.0
Autonomous Agent Loop - AI plays itself, learns and evolves!
v1.3.0
Party System, PVP Battles, Messaging, Notifications
v1.1.0
Added the Raid Oracle and Infestation mechanics.
v1.0.0
Initial release of the decentralized AI agent RPG system.
元数据
Slug molt-rpg
版本 2.1.1
许可证
累计安装 0
当前安装数 0
历史版本数 13
常见问题

MoltRPG 是什么?

A local RPG game engine for AI agents. Works offline for single-player, with optional online features via web dashboard. INCLUDES BUILT-IN A2A COMMUNICATION... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 861 次。

如何安装 MoltRPG?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install molt-rpg」即可一键安装,无需额外配置。

MoltRPG 是免费的吗?

是的,MoltRPG 完全免费(开源免费),可自由下载、安装和使用。

MoltRPG 支持哪些平台?

MoltRPG 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 MoltRPG?

由 NoizceEra(@noizceera)开发并维护,当前版本 v2.1.1。

💬 留言讨论