Gold Daily Report
v1.0.0每日金价快报 - 国际现货(XAU/USD) + 国内Au99.99 + 近期资讯。运行 scripts/gold_report.js 获取报告并发送给用户。
⭐ 0· 29·0 current·0 all-time
by@poyobi
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (gold price report) align with included script and SKILL.md. The script only fetches market data and news and formats a report; it does not request unrelated permissions or credentials.
Instruction Scope
SKILL.md instructs running scripts/gold_report.js and having the agent capture output and send it to channels (feishu/telegram). The script itself only prints to stdout; sending requires the agent's normal channel integrations. This is expected but the SKILL.md assumes the agent has permission to post to those channels — confirm channel integrations before enabling automated delivery.
Install Mechanism
No install spec; this is instruction+code only. No dependencies are declared in package.json and the script uses only Node built-in http/https — no remote downloads or archive extraction are performed.
Credentials
The skill declares no environment variables or credentials. The script accesses only public HTTP(S) endpoints (gold-api, eastmoney, er-api, sina). It does not read local config, secrets, or other environment variables.
Persistence & Privilege
Flags show always:false and normal user-invocable/autonomous invocation defaults. The skill does not request persistent system-wide changes or modify other skills' configs.
Assessment
This skill appears to do exactly what it claims: periodically fetch public gold prices and recent headlines, format a report, and print it. Before installing: confirm you want automated postings (the agent will need permission to send messages to Feishu/Telegram if you enable cron/automation), be aware it fetches and scrapes third‑party public sites (which can be brittle or blocked), and validate that automatic scheduling/forwarding behavior is acceptable in your environment. If you need the agent to actually post reports, ensure channel integrations are configured and that no sensitive credentials will be exposed by the agent when sending messages.Like a lobster shell, security has layers — review code before you run it.
latestvk977n3y3b9w997s2q7y4fe5af5848hm8
License
MIT-0
Free to use, modify, and redistribute. No attribution required.