Skills/ClawHub/1688-shop-health-check

1688-shop-health-check@1.4.0

VERIFIED· install only

Publisher claims: "1688 店铺生意体检。基于流量、询盘、成交、商品、客户、广告、风险七大维度进行全面健康诊断（成交维度覆盖成交、订单履约与买家评价，风险维度专注合规扣分），输出总结性结论 + HTML 网页数据报告，支持多店铺批量体检；报告后可基于优先行动建议展示可多选交互卡片，继续执行对应优化动作，并可按条件引导用户设置每日定时体检任务。 本 Skill 的完整流程（意图确认 → 七维度诊断 → 结论输出 → HTML 报告 → 行动项选择）已由 workflow `1688-shop-health-check` 编排覆盖，命中 whenToUse（店铺体检、健康检查、店铺诊断、店铺分析、经营分析、全面诊断、店铺经营状况、体检报告）时直接执行 workflow，不加载本 SKILL.md。" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher 1688aiinfra · publishing for 187 daysInstalls 1,089Last detonated 7d ago
$clawhub install 1688-shop-health-check
WatchReport an issue

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 2026-11-07 and scored it 80/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsSKILL.md:641 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files## 十、环境变量（.env）Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Destructive file system command detectedworkflow/health-check.js:798 · Destructive file system command detected? `del /f /q "${d}${_sep}_wf*.json" 2>nul & rmdir "${d}" 2>nul`Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/_tracker.py:8 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files环境变量（从项目根目录 .env 读取）：Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/_tracker.py:39 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# 模块加载时解析一次 .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/_tracker.py:24 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files"""解析项目根目录的 .env 文件，将变量注入 os.environ（已有环境变量不覆盖）。"""Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:643 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files项目根目录的 `.env` 文件存储 skill 基础信息，供埋点上报模块读取。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
Python subprocess execution detectedscripts/batch_fetch.py:106 · Python subprocess execution detectedproc = subprocess.run(Fix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Dense URL-encoded contentscripts/_auth.py:83 · Dense URL-encoded content — may be obfuscating payloads转换为：/api/v1/user?age=20&name=%E5%BC%A0%E4%B8%89Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
HIGH
Destructive file system command detectedworkflow/health-check.js:83 · Destructive file system command detected? (capture ? `del /f /q "${errF}"` : `del /f /q "${outF}" "${errF}"`)Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/_tracker.py:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_path = _ROOT_DIR / ".env"Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsSKILL.md:651 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files> 已存在的系统环境变量优先级高于 `.env`，CI/CD 注入的变量不会被覆盖。Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05

Cost to the agent

Instructions loaded
≈6,362 tok
1 file · 78 in bundle

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.