super-stock-trading@1.0.0
BLOCKED· install onlyPublisher claims: "超级股票操盘 Skill —— 面向 A 股个人投资者的全流程操盘智能体 Skill 包。整合 137 个细粒度 Skills 与 31 位数字人专家,并内置《短线金手》七册实战战法体系(私募盈利系统/经典形态/涨停狙击/急速拉升/分时图/T+0/K线精通),覆盖盘前分析、盘中决策、盘后复盘、选股、持仓体检、月度组合管理等完整投资闭环。 何时使用本 Skill:当用户提到「股票操盘」「盘前分析」「盘后复盘」「选股」「持仓体检」「月度组合管理」「仓位管理」「止损止盈」「板块轮动」「题材挖掘」「龙头战法」「财报季」「公告解读」「资金面」「北向资金」「龙虎榜」「风险体检」「组合再平衡」「定投」「指数基金」「期权对冲」「产业链」「护城河」「估值」「黑马」「打板」「异动」等关键词,或提到「短线」「涨停」「集合竞价」「分时图」「T+0」「主力吸筹」「仙人指路」「黄金十字」「梅开二度」「大长腿」「黄金分割」「急速拉升」等短线战术关键词,或需要系统性地完成 A 股投研—交易—风控—复盘工作时,应启用本 Skill。 能力边界:主要服务于 A 股(沪深京)及与之相关的港股通、ETF、可转债、期权等品种的研究与决策辅助;不提供直接下单通道,所有交易建议均需用户人工二次确认;不构成任何投资建议,最终决策与盈亏由用户自行承担。" Observed in sandbox: reads credential files, sends data to fd12:ea5f:789c:1:d000:2b:95f6:3c3a, 10.246.60.58, www.skills.sh.
Coverage
Install scripts ran; no agent task scenario for this bundle.- Tested
- install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · 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 (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-12 and scored it 24/100 (Blocked). Do not install it: the sandbox observed behaviour consistent with credential theft, exfiltration or persistence. Notable findings: Pipe-to-shell pattern; Privileged sudo command; Access to sensitive file paths. Summary: reads credential files, sends data to fd12:ea5f:789c:1:d000:2b:95f6:3c3a, 10.246.60.58, www.skills.sh.
Behavior trace
Honeypot run · 29 s · 2 scenariosStatic findings
log_warn "未找到 npx,Wind AIFin Market Skill 将跳过。安装: curl -fsSL https://fnm.vercel.app/install | bash"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.log_ok "npx: $(npx --version 2>&1)"Fix: Pin versions and sources; vendor anything fetched at install time.# 4. 安装 Wind AIFin Market skills(npx skills add)Fix: Pin versions and sources; vendor anything fetched at install time.log_err "未找到 python3,请先安装: sudo apt install python3 python3-venv"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# 复制本文件为 .env 并填入真实凭证后使用Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.log_warn "未找到 npx,Wind AIFin Market Skill 将跳过。安装: curl -fsSL https://fnm.vercel.app/install | bash"Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# 1. 检查前置环境(git / python3 / node / npx / clawhub)Fix: Pin versions and sources; vendor anything fetched at install time.if command -v npx &>/dev/null; thenFix: Pin versions and sources; vendor anything fetched at install time.# 安装 Wind AIFin Market Skills(npx skills add)Fix: Pin versions and sources; vendor anything fetched at install time.# chmod +x install.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# 注意:切勿将含有真实密钥的 .env 文件提交到版本控制系统Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.log_err "未找到 git,请先安装: sudo apt install git / brew install git"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.
What would make this Verified
56 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%An override rule (credential_read_plus_egress) caps this verdict regardless of the score. The first item below has to go before anything else counts.
- Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs.
- Contacts a host you did not declare≈ +23 on the totalList every host you talk to in SKILL.md frontmatter (`network: [api.example.com]`), or stop contacting the ones you cannot justify.
- Pipe-to-shell pattern≈ +9 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
- Unclaimed publisher≈ +8 on the totalClaim yjkj999999: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.