yumfu@1.7.12
VERIFIED· install onlyPublisher claims: "Multiplayer text RPG with 12 playable worlds — play together in Telegram groups! Worlds include 笑傲江湖, Harry Potter, Warrior Cats, F15 Down, 龙虾三国, 倚天屠龙记, Game of Thrones, Lord of the Rings, 西游记 (Journey to the West), 罗摩衍那 (Ramayana), 大唐西域记 (Xuanzang), 内裤超人 (Captain Underpants), and 战国乱世 (Sengoku Chaos). Each player gets their own character in a shared world with AI art every scene. PvP, team quests, natural language — no commands needed. Use when: /yumfu, group RPG, text adventure, 武侠, 西游记, 孙悟空, 罗摩衍那, 罗摩, 悉多, 哈奴曼, Ramayana, LOTR, 指环王, 权力的游戏, 三国, 张无忌, 战国, 织田信长, 丰臣秀吉, 德川家康, 武田信玄." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-08 and scored it 82/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
## ⚠️ CRITICAL: Always Use This Skill for Game Sessions!Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.@import url('https://fonts.googleapis.com/css2?family=Noto+Serif+SC:wght@400;600;700&display=swap');Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.near the fresh-kill pile while apprentices practice battle moves...Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.proc = subprocess.run(cmd, capture_output=True, text=True)Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.ai_response = "You see the ThunderClan camp bustling with activity. Warriors share tongues near the fresh-kill pile..."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.…ield into clues. Someone nearby now understands that this place is not merely a kill ground, but a hinge point in {quest_name}. A scavenger, watcher, or hidden serva…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.