AI保险助手
v1.7.11中国大陆保险AI助手。当用户询问以下内容时使用：保险配置、保险方案、产品对比、重疾险/医疗险/寿险/意外险/储蓄险推荐、保费计算、保障缺口分析、需求分析、核保合规、理赔、朋友圈文案、培训话术、代理人展业支持。
⭐ 0· 173·1 current·1 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (中国大陆保险助手) match the included assets: a large products.json, compliance and knowledge references, and three Python scripts for needs analysis, plan design and premium calculation. Minor mismatch: SKILL.md expects to run 'python3 scripts/...' but registry metadata lists no required binaries — the skill effectively requires a Python 3 runtime to operate.
Instruction Scope
Runtime instructions call local scripts and read local reference files (products.json, insurance-knowledge.md, compliance.md). The skill collects personal insurance-related inputs (age, income, mortgage, existing coverages) which is appropriate for its purpose; there are no instructions to read unrelated system files or to transmit data to external endpoints.
Install Mechanism
No install spec and all code/data are bundled with the skill. No network downloads or external package installs are performed by the skill itself, reducing installation risk.
Credentials
The skill declares no environment variables, credentials, or config paths. It operates on local static data and user-supplied inputs only. Note: it will process sensitive personal data (PII/health/financial) by design — this is proportional but requires appropriate operational safeguards.
Persistence & Privilege
always:false and no evidence of modifying other skills or system-wide configuration. The skill runs on demand and does not request elevated or persistent platform privileges.
Assessment
This skill appears coherent and implements what it claims, but check the following before enabling: 1) Ensure Python 3 is available where the skill will run (SKILL.md runs 'python3' though required binaries are not declared). 2) The skill processes sensitive personal data (age, health, income, mortgage, existing policies) — only use in environments that comply with local data-protection requirements (e.g., obtain consent, store/handle PII per law). 3) Review references/products.json for data accuracy, licensing, and freshness (the file is large and contains product listings). 4) If you plan to allow autonomous agent invocation, supervise initial runs — the skill can generate sales/marketing copy and may prompt for contact sharing; ensure those outputs meet your compliance and ethical rules. 5) If you need stronger assurance, open the three scripts (they are short) to confirm there are no hidden network calls or external endpoints (review shows none), and run them in a sandboxed environment first.Like a lobster shell, security has layers — review code before you run it.
advisorvk9769n5gsgcy8nam5nt2zttgqd84z9wdchinavk9769n5gsgcy8nam5nt2zttgqd84z9wdinsurancevk9769n5gsgcy8nam5nt2zttgqd84z9wdlatestvk9769n5gsgcy8nam5nt2zttgqd84z9wd
License
MIT-0
Free to use, modify, and redistribute. No attribution required.