undercover-is-who

担任谁是卧底游戏法官，负责分词、流程主持、描述记录、投票统计、淘汰判定及游戏结束回顾，全程保密身份。

This skill appears to do exactly what it says: run locally to manage a “谁是卧底” game, assign roles, record descriptions and votes, and generate messages. Before installing or invoking it, consider: (1) Persistence/privacy: the skill creates database/games.db inside the skill folder and stores player names and message-sender IDs — if your agent runs in a shared environment, those IDs and game logs could be accessible to others; plan for secure storage or periodic cleanup. (2) Message delivery: the skill assumes the agent will send private messages and has access to message-sender IDs; ensure your agent/platform integration can deliver private DMs and that you give only the minimum required privileges. (3) Disclosure behavior: final vote-announcement logic prints who voted for whom — this is a normal gameplay option but is more revealing than “only who has/hasn’t voted”; review the code if you need a different privacy posture. (4) No external network or secrets are requested by this skill, and there is no install-time download risk. If you need higher assurance, inspect the remaining truncated parts of db.py/game_engine.py to confirm there are no unexpected network calls or hidden behaviors and run the skill in an isolated environment first.

Type: OpenClaw Skill Name: undercover-is-who Version: 1.0.0 The skill bundle implements a 'Who is Undercover' (谁是卧底) party game judge. It uses a structured approach with Python scripts (game_engine.py, vote_handler.py, describe_handler.py) and a local SQLite database (database/games.db) to manage game state, player roles, and voting. The SKILL.md instructions use strong language ('Constitution-level') to ensure the AI agent maintains game integrity and secrecy, which is a functional requirement for this game type rather than a malicious prompt injection. No evidence of data exfiltration, unauthorized network access, or malicious command execution was found.