lgd-fin-guard

把“有籍·有证·有门禁”的LGD三律翻译进金融/持牌机构AI场景（投顾、风控、反洗钱），通过命令行脚本对AI系统做合规自评，输出通过/拒绝结论及具体缺失项。声明为零依赖、本地运行。

zhaoxinghua09-cell

热度 61.88

最近更新 2026-10-17 07:41:51

分类：安全依赖：代码执行应用场景：财务 / 法律文档 / 报告撰写 / 工作流

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add lgd-fin-guard

Metadata

name: lgd-fin-guard
description: lgd-fin-guard — 把 LGD 三律（有籍·有证·有门禁）翻译进金融 / 持牌机构 AI 应用（投顾·风控·反洗钱）的合规守门器，对 AI 系统做三律自评与门禁判定（零依赖）。适用场景：当需要金融AI合规守门能力时使用本技能；触发词：lgd-fin-guard。
slug: lgd-fin-guard
version: 1.0.1
display_name: 金融AI合规守门
display_name_en: Finance AI Compliance Guard
agent_created: true
author: XLGD · 诺声(Logos)@SynomosAI
license: MIT
license_scope: 代码（.py 文件）MIT；本 SKILL.md 与其中理论文本不在 MIT 覆盖范围内（见文末「License & attribution」）
allowed-tools: Read, Glob, Grep, Bash, Write, WebFetch
category: AI 治理
platforms: ["windows","macos","linux"]
copyright: XLGD · SynomosAI
description_zh: lgd-fin-guard — 把 LGD 三律（有籍·有证·有门禁）翻译进金融 / 持牌机构 AI 应用（投顾·风控·反洗钱）的合规守门器，对 AI 系统做三律自评与门禁判定（零依赖）。
description_en: Translate the LGD three laws into financial licensed-institution AI (advisory, risk control, AML): three-law self-assessment and gate decisions (zero-dependency).
classification: {"skillhub":["ai-governance"],"iso_25010":["Security","Maintainability"]}
risk_tier: medium
risk_rationale: 门禁批量补丁默认 medium（按默认策略设计为中等风险）：调用 API/读写文件/本地执行，最小权限，密钥走 Secret；若实际涉对外代执行(push/发布/发送/上架)须人工复评，改 high 并走人工批准。
tags: ["lgd-fin-guard","AI 治理","金融合规","持牌机构"]
read_when: ["金融 AI 系统上线前要确认算法模型具备投顾/风控持牌资质","外部数据接入前要校验源端是否满足有籍·有证身份认证","高敏感交易决策（信贷审批/大额转账）触发前要准入门禁判定","用户说「这个风控模型上线合规吗」"]
ai_protocol: true
spec: usk/1.0
interface: {"type":"cli","entry_point":"scripts/fin_guard.py","runtime":"python3","call_pattern":"args"}
input_schema: {"args":{"type":"string","description":"命令行参数透传给主脚本，具体取值见各包 --help","required":false}}
output_schema: {"stdout":{"type":"string","description":"标准输出为 JSON 结果，含逐项检查与总体结论"},"exit_code":{"type":"integer","description":"0=PASS/完成；1=FAIL/有警告或待补强；2=用法或参数错误"}}
capabilities: ["cli_tool"]
permissions: {"network":false,"filesystem":false,"subprocess":false}
requirements: {"python_packages":[],"min_python":"3.8"}
changelog: 1.0.1: Bilingual rewrite (full EN+ZH, English first), added read_when; 1.0.0: initial upload (USK v3)

凡自治之物 · LGD 治理学 · 创造术家族｜评测协议：见平台质量门禁规范

English

When to use

Before a financial AI system goes live, to confirm the algorithm model holds advisory or risk-control licensed qualifications.
Before external data ingestion, to check that the source meets the "registered · evidenced" identity-authentication requirement.
As the admission gate before high-sensitive transaction decisions (credit approval, large transfers) are triggered.

Usage

Call the core script fin_guard.py to run the compliance check, with configurable check dimensions. Example: python fin_guard.py --mode=guard --entity=<AI system id> --scope=qualification/permission. Here --mode is audit or gate, and --entity is the model or business ID under check.

Workflow

Identify the AI application module under compliance verification and its associated business scenario.
Run python fin_guard.py, passing the entity ID and the three-laws determination mode.
The script reads the files and performs the internal LGD three-laws (registered · evidenced · gated) self-assessment.
Generate the compliance verdict report, stating pass/reject and the specific missing items.
The system automatically allows passage or blocks the data flow based on the result.

Evidence & safety statement

Evidence: TBD (no evaluation / badge link yet; update here once it is produced)
Version: 1.0.1
Security: no independent security scan has been performed (TBD); the conclusion is pending and no endorsement is given until it is completed.

中文

何时用

金融 AI 系统上线前，需确认算法模型具备投顾或风控持牌资质。
外部数据接入前，校验源端是否满足“有籍·有证”身份认证要求。
高敏感交易决策（如信贷审批、大额转账）触发前的准入门禁判定。

用法

调用核心脚本 fin_guard.py 执行合规检查逻辑，支持参数配置校验维度。例如：python fin_guard.py --mode=guard --entity=<AI 系统标识> --scope=资质/权限，其中--mode设定为audit(审计)或gate(门禁)，--entity填入待校验的模型或业务 ID。

流程

确认待合规验证的 AI 应用模块及其关联的业务场景需求。
执行 python fin_guard.py 命令，传入实体标识与三律判定模式参数。
脚本读取文件资料对 LGD 三律（有籍·有证·有门禁）进行内部自评计算。
生成合规判定报告，明确通过/拒绝状态及具体缺失项。
系统根据结果自动执行允许通行或阻断数据流的动作。

证据与安全声明

证据：TBD（暂无评测/徽章链接；产生后在此更新实际链接）
版本：1.0.1
安全：未做独立安全扫描（TBD），结论待补；补全前不作推荐背书。