ClawHub

Game - Endless Downstairs

v1.0.3

Interactive interface for the text adventure game Endless Downstairs, providing game state management and event selection handling; use when users want to pl...

⭐ 1· 137·0 current·0 all-time
bySean Gao@gsc578045031-cloud
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name/description (Endless Downstairs text adventure) matches the bundle contents: Python game engine, i18n, and JSON event data. There are no unrelated environment variables, binaries, or external services required.
✓
Instruction Scope
SKILL.md instructs the agent to translate user input into specific local CLI commands (python game.py ...). Those commands map to the provided game.py and engine code. The instructions do not ask the agent to read unrelated files, environment variables, or transmit data externally. They do instruct the agent to execute the repository's Python code, which is expected for a game skill.
✓
Install Mechanism
No install spec is present (instruction-only skill). The repository includes source code but there is no automated download-from-URL or external package install declared by the skill itself, so no installer-side risk is introduced by the skill metadata.
✓
Credentials
The skill declares no required env vars, credentials, or config paths. The code does read and write local project files (save.json, checkpoints.json, config.json) which is coherent with game save and language persistence features. It does not access OS credentials, network endpoints, or unrelated config.
✓
Persistence & Privilege
always:false and default model-invocation behavior. The skill writes local save/config files within the repository (save.json, checkpoints.json, config.json) which is normal for a game. It does not modify other skills or system-wide agent settings.
Assessment
This skill is a local Python text-adventure and appears internally consistent. Before installing or running it: 1) be aware the agent will be asked to run the repository's Python scripts (python game.py ...). Executing third-party code runs with the host user's privileges—only proceed if you trust the source. 2) The game reads/writes local files (save.json, checkpoints.json, config.json) in the repository directory and may update config.json when you change language. 3) There are no network calls or credential requests in the visible code, but if you install from an external URL (README suggests a GitHub repo), confirm the repository origin. 4) If you are concerned, run the code in an isolated environment (container or VM) or review the remaining omitted files for unexpected behavior before letting the agent execute commands.

Like a lobster shell, security has layers — review code before you run it.

latestvk977jdcnxaca8bgnmm2ht9a22d83cpsk

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments