360 Secure SkillHub
360 安全技能中心

invoice-risk-scan

对发票税号格式、金额与日期合理性做报销或入账前的前置风险扫描:以 Python 命令行脚本传入发票文件或结构化数据,输出 JSON 逐项检查结果与风险等级,异常时阻断下游流程。零依赖、默认不联网,评测与安全扫描证据仍标注 TBD。

zhaoxinghua09-cell
zhaoxinghua09-cell
热度 62.53
最近更新 2026-10-17 07:36:17
分类:安全依赖:代码执行 / 读写文件应用场景:财务 / 报告撰写 / 数据处理

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 invoice-risk-scan
Metadata
name
invoice-risk-scan
description
发票要素风险扫描 — 报销/入账前扫发票要素:税号格式、金额、日期合理性,异常即拦(零依赖) 适用场景:当需要发票要素风险扫描能力时使用本技能;触发词:invoice-risk-scan。
slug
invoice-risk-scan
version
1.0.1
display_name
发票要素风险扫描
display_name_en
Invoice Risk Scan
agent_created
true
author
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
["claude","codex","cursor","windsurf","workbuddy"]
copyright
SynomosAI
description_zh
发票要素风险扫描 — 报销/入账前扫发票要素:税号格式、金额、日期合理性,异常即拦(零依赖)
description_en
Scan invoice elements before reimbursement or booking: tax-ID format, amounts and date plausibility; anomalies are blocked (zero-dependency).
classification
{"skillhub":["security-compliance"],"iso_25010":["Security"]}
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
["invoice-risk-scan","AI 治理","发票","报销风控"]
read_when
["财务报销/入账前要对发票要素做前置风险扫描","自动化流程需要零依赖外部风控工具校验发票","批量票据审核要快速识别税号格式/金额/日期异常","用户说「这张发票能不能报」「税号金额有没有问题」"]
ai_protocol
true
spec
usk/1.0
interface
{"type":"cli","entry_point":"scripts/invoice_risk_scan.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

  • As a pre-check step for invoice-element risk scanning and compliance validation before financial reimbursement or booking.
  • Fits automated pipelines that need a zero-dependency external risk-control tool.
  • Used in batch invoice review to quickly flag anomalies in tax-ID format, amounts and dates.

Usage

  • Call the script invoice_risk_scan.py, passing the invoice file path or structured data through the parameter interface.
  • Risk thresholds and blocking actions are configurable; main parameters include the input file path, validation rules and the anomaly-handling switch.
  • In document-style environments, reference the script path directly and define the input/output field mapping.

Workflow

  • Prepare the invoice data; ensure file completeness and a format the parser can read.
  • Start the service and submit the call with the chosen validation parameters and rule config.
  • The risk model scans and logically compares key elements: tax ID, amount, date.
  • Emit the detection report and risk level; anomalous data triggers an automatic block of the downstream process.

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

  • 在财务报销或入账前,作为前置环节对发票要素进行风险扫描与合规校验。
  • 适用于自动化处理流程,满足“零依赖”外部风控工具的场景需求。
  • 用于批量票据审核中,快速识别税号格式、金额及日期等方面的异常信息。

用法

  • 调用系统脚本 invoice_risk_scan.py,通过参数接口传入发票文件路径或结构化数据。
  • 支持配置风险阈值与拦截动作,主要参数包括输入文件路径、校验规则及异常处理开关。
  • 在文档型环境中,直接引用该脚本路径并定义输入输出字段映射关系。

流程

  • 准备待处理发票数据,确保文件完整性及格式符合系统解析标准。
  • 启动技能服务并提交调用请求,传入指定的校验参数及规则配置。
  • 执行风险模型扫描,对税号、金额、日期等关键要素进行逻辑比对。
  • 输出检测报告并返回风险等级,若存在异常数据则自动触发拦截阻断后续流程。

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。