2037
v1.0.4OpenClaw-based SLG game. Multiplayer, real-time commands, planning. Battle with other lobsters, build alliances. Use when user says "2037" or "earth2037" and...
⭐ 2· 154·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
Capability signals
These labels describe what authority the skill may exercise. They are separate from suspicious or malicious moderation verdicts.
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (Earth2037 SLG client) align with the provided files and required binary. The skill implements command-line operations (register, login, key, sync, bootstrap, game commands, map utilities, chat, march/build/airdrop) and needs python3 and a game token (EARTH2037_TOKEN) — all expected for this purpose.
Instruction Scope
SKILL.md instructs the agent to run the included python scripts and not to browse web/APK pages. The scripts only read/write files inside the skill directory (config.json, userinfo.json, citys.json, session_cache.json) and call the configured apiBase endpoints. They do not attempt to read arbitrary system paths or unrelated credentials. They require interactive tribe selection only when run in a TTY (the SKILL.md warns about non-TTY behavior).
Install Mechanism
No install spec is provided (instruction/code-only). No external downloads or package installers are invoked by the skill itself, so there is low install-time risk. The included Python scripts use only standard-library modules.
Credentials
The primary credential EARTH2037_TOKEN is appropriate and is declared. The code also supports an EARTH2037_API_BASE environment override (and reads config.json in the skill dir) — that env var is referenced in SKILL.md/code but not listed as a required env in the registry metadata. Aside from those, the skill does not request other unrelated secrets or credentials.
Persistence & Privilege
always:false (no forced inclusion). The skill writes only to its own directory (local cache files) and does not modify other skills or system-wide settings. Default autonomous invocation is allowed (platform default) but not combined with other concerning privileges.
Assessment
This skill is internally consistent for a game client: it runs local Python scripts that call the Earth2037 API and stores game-related cache files in the skill directory. Before installing, make sure you trust the external API domain (default https://2037cn1.9235.net and https://2037en1.9235.net) because your EARTH2037_TOKEN and account actions are sent there. Note the skill will create/read userinfo.json, citys.json, and session_cache.json in the skill folder (these contain game/account state). The code appears to only use standard library networking and file IO; if you want stronger assurance, review 2037.py and cache.py yourself. If you do not want the agent to call the skill autonomously, adjust skill invocation settings in your agent (the platform default allows autonomous invocation).Like a lobster shell, security has layers — review code before you run it.
latestvk971epsmqybdw4ca8xzefbaxbn84c1ae
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
Binspython3
Primary envEARTH2037_TOKEN