What makes Financial Fraud Analyzer Lite notable?

1.2K downloads. Trust evidence available

How should Financial Fraud Analyzer Lite be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Financial Fraud Analyzer Lite

财务造假风险分析技能。基于财务报表（利润表、资产负债表、现金流量表）评估盈余操纵与会计舞弊概率，输出结构化风险结论与证据链。支持单公司深度分析和批量筛查。Use when user asks to detect financial statement fraud, earnings manipulation, a... Skill: Financial Fraud Analyzer Lite Owner: hollis9087 Summary: 财务造假风险分析技能。基于财务报表（利润表、资产负债表、现金流量表）评估盈余操纵与会计舞弊概率，输出结构化风险结论与证据链。支持单公司深度分析和批量筛查。Use when user asks to detect financial statement fraud, earnings manipulation, a... Tags: analysis:1.0.0, finance:1.0.0, fraud:1.0.0, latest:1.0.1 Version history: v1.0.1 | 2026-04-30T07:38:14.436Z | auto - Major simplification: large codebase cleanup—removed 97 files, retaining

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.2k

Updated

Oct 10, 2026

Version

1.0.1

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/10/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 10, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 10, 2026
Adoption signal: 1.2K downloadsadoption · observed Oct 10, 2026
Latest release: 1.0.1release · observed Apr 30, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s177cqfxj8hyd271e27az0p2nx85tds8:holli-financial-fraud-analyzer

Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-hollis9087-holli-financial-fraud-analyzer/snapshot"

Documentation

CLAWHUB

74,507 characters of source documentation, loaded on request.

Extracted files

4 files captured from the source.

SKILL.md

---
name: financial-fraud-analyzer
description: 财务造假风险分析技能。基于财务报表（利润表、资产负债表、现金流量表）评估盈余操纵与会计舞弊概率，输出结构化风险结论与证据链。支持单公司深度分析和批量筛查。Use when user asks to detect financial statement fraud, earnings manipulation, accrual quality problems, or suspicious accounting signals from company filings. Supports both single-company deep analysis and batch screening.
---

# 财务造假风险分析（Financial Fraud Analyzer v2）

按以下流程执行，并始终保持"证据优先、结论谨慎"。

## 版本更新（v2）

- ✅ 新增：Dechow F-Score（应计质量模型）
- ✅ 新增：行业分组阈值（科技/制造/消费/金融）
- ✅ 新增：批量筛查模式（支持10+公司快速扫描）
- ✅ 新增：SEC EDGAR API 自动数据获取
- ✅ 优化：三层证据整合框架
- ✅ 验证：已在 AAPL/MSFT/TSLA/NVDA 等12家公司测试

## 0) 任务边界（必须先说清）

- 明确这是**风险筛查**，不是司法定性。
- 结论表述使用：`低/中/高风险`，避免"已造假"的确定语气。
- 若数据缺失，明确标注"无法判断"的环节。

## 1) 数据输入清单（至少2期，建议3-5期）

优先收集：

- 利润表：营业收入、营业成本、销售费用/管理费用（SG&A）、折旧摊销、净利润（或持续经营利润）
- 资产负债表：应收账款、存货、流动资产、固定资产净额（PP&E）、长期投资/证券、总资产、流动负债、长期有息负债
- 现金流量表：经营活动现金流（CFO）

如口径不一致（合并/母公司、会计准则变更），先对齐口径再计算。

## 2) 快速红旗扫描（先看异常形态）

先做方向性判断，命中越多，后续审查越深：

1. 营收增速显著高于经营现金流增速
2. 应收账款增速长期高于营收增速
3. 存货增速长期高于营收增速
4. 毛利率异常波动但同行无类似变化
5. 折旧率突然下降（可能延长折旧年限）
6. 资本化比例上升、费用化下降（利润被"美化"）
7. 关联交易或非经常性损益对利润贡献过大
8. 审计意见变化、内控缺陷、频繁更换审计师

## 3) 量化模型计算（核心）

### A. Beneish M-Score（8变量）

使用 `references/beneish-formulas.md` 的定义与公式计算：

- DSRI, GMI, AQI, SGI, DEPI, SGAI, LVGI, TATA
- 线性组合得到 M-Score

解释规则（行业分组阈值）：

**通用阈值**：
- `M-Score > -2.22`：盈余操纵风险偏高
- `M-Score <= -2.22`：未见明显操纵信号

**行业调整阈值**（参考 `references/industry-thresholds.md`）：
- 科技/互联网：`-2.10`（高增长容忍度）
- 制造业：`-2.22`（标准阈值）
- 消费品：`-2.30`（稳定性要求更高）
- 金融业：不适用 Beneish（需专用模型）

### B. Dechow F-Score（应计质量）

详见 `references/dechow-fscore.md`。

核心公式：
`F-Score = -4.255 + 1.191*RSST_Accruals + 0.057*ΔCash_Sales + 0.691*ΔReceivables + 0.179*ΔInventory + 0.124*%Soft_Assets + 0.303*ΔCash_Margin + 0.116*ΔROE`

解释：
- `F-Score > 1.0`：高应计质量风险
- `F-Score <= 1.0`：应计质量可接受

### C. 现金-利润一致性

至少计算：

- `CFO / 净利润`
- `应计项比率 = (净利润 - CFO) / 总资产`

经验解释：

- `CFO/净利润` 长期显著低于 1，且应计项比率持续偏高 → 利润质量可疑

### D. 结构性对比（趋势 + 同行）

对以下指标做**时间趋势**与**同行横向对比**：

- 应收周转天数、存货周转天数
- 毛利率、期间费用率
- 资本开支与折旧比
- 资产负债率、短债压力

## 4) 三层证据整合（防止单指标误判）

必须同时给出三层证据：

1. **模型证据**：M-Score 与关键比率是否异常
2. **财务逻辑证据**：利润、现金流、营运资本是否一致
3. **治理与披露证据**：审计意见、关联交易、会计政策变更说明

若三层证据仅有一层异常，结论降级为"观察风险"；
若三层证据多数一致异常，结论升级为"高风险"。

## 5) 输出格式（固定模板）

按以下结构输出，避免散乱描述：

### 5.1 执行摘要（<= 150字）
- 风险等级：低 / 中 / 高
- 最关键的2-3条证据
- 下一步建议

### 5.2 指标总表（必须表格）
列：`指标 | 本期 | 上期 | 变化 | 风险信号(是/否) | 解释`

### 5.3 Beneish分解（必须表格）
列：`变量 | 数值 | 对风险的含义`
并给出最终 M-Score 与阈值比较。

### 5.4 红旗清单
- 已命中红旗（按严重程度排序）
- 未命中但需持续跟踪的红旗

### 5.5 结论与行动建议
- 结论：低/中/高风险（附置信度）
- 建议动作：
  - 立即补充哪些披露材料
  - 是否需要深入核查（如函证、渠道访谈、供应链交叉验证）

### 5.6 局限性（必须写）
- 数据缺失/口径差异/行业季节性等可能影响。

## 6) 质量门槛（输出前自检）

输出前逐条检查：

- [ ] 是否明确"风险筛查≠定罪"
- [ ] 是否给出可复核公式与关键数据来源
- [ ] 是否有"趋势+同行"双重比较
- [ ] 是否包含局限性说明
- [ ] 是否给出具体下一步核查建议

## 7) 脚本工具

### 单公司分析

若用户提供了结构化数字，运行：

```bash
python scripts/beneish_mscore.py --input data.json
```

### 批量筛查（10+ 公司）

自动从 SEC EDGAR 获取数据并计算：

```bash
python scripts/fetch_and_analyze.py
```

输出：
- `tmp/beneish_batch_results.json`：完整结果
- 终端：汇总表格（Ticker | M-Score | Risk | CFO/NI）

#

_meta.json

{
  "ownerId": "kn79q2kj15j98d5cqxw95sfd0185vax5",
  "slug": "holli-financial-fraud-analyzer",
  "version": "1.0.1",
  "publishedAt": 1777534694436
}

skill-card.md

## Description:

Financial Fraud Analyzer Lite helps agents screen financial statements for earnings manipulation and accounting fraud risk using Beneish M-Score, Dechow F-Score, cash-flow checks, and structured evidence summaries.

This skill is ready for commercial/non-commercial use.

## Publisher:

[hollis9087](https://clawhub.ai/user/hollis9087)

### License/Terms of Use:

MIT-0

## Use Case:

External users, analysts, and developers use this skill to screen company financial statements for manipulation risk and generate cautious low, medium, or high risk findings with supporting tables and follow-up checks.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: Users could treat a model score or risk label as proof of financial fraud.

Mitigation: Frame every result as risk screening, include data limitations, and require corroborating disclosure, audit, governance, and cash-flow evidence before action.

Risk: Formula, threshold, or input-data mismatches could produce misleading company risk rankings.

Mitigation: Verify formulas, thresholds, financial-statement mappings, and local data paths before relying on outputs.

Risk: The workflow is Chinese-first and includes sample China equities data, which may not match all users' reporting regimes or terminology.

Mitigation: Confirm accounting standards, period alignment, translations, and jurisdiction-specific reporting conventions before comparing results.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/hollis9087/skills/holli-financial-fraud-analyzer)

## Skill Output:

**Output Type(s):** [Text, Markdown, Shell commands, Guidance]

**Output Format:** [Markdown analysis with tables, risk labels, limitations, and optional JSON calculation output]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Outputs are screening signals, not determinations of fraud.]

## Skill Version(s):

1.0.1 (source: server release evidence)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

china_stocks_2023_2022.json

{
  "600519.SH": {
    "name": "贵州茅台",
    "2023": {
      "sales": 149871000000,
      "cogs": 11284000000,
      "receivables": 1580000000,
      "current_assets": 195800000000,
      "ppe_net": 18500000000,
      "long_term_investments": 2800000000,
      "total_assets": 267400000000,
      "depreciation": 1200000000,
      "sga": 18900000000,
      "current_liabilities": 89500000000,
      "long_term_debt": 500000000,
      "income_cont_ops": 74780000000,
      "cfo": 82300000000
    },
    "2022": {
      "sales": 127100000000,
      "cogs": 9800000000,
      "receivables": 1200000000,
      "current_assets": 172000000000,
      "ppe_net": 17800000000,
      "long_term_investments": 2500000000,
      "total_assets": 238600000000,
      "depreciation": 1100000000,
      "sga": 16200000000,
      "current_liabilities": 76800000000,
      "long_term_debt": 400000000,
      "income_cont_ops": 62710000000,
      "cfo": 68900000000
    }
  },
  "000858.SZ": {
    "name": "五粮液",
    "2023": {
      "sales": 81760000000,
      "cogs": 15200000000,
      "receivables": 890000000,
      "current_assets": 98500000000,
      "ppe_net": 28900000000,
      "long_term_investments": 1200000000,
      "total_assets": 158700000000,
      "depreciation": 1800000000,
      "sga": 12300000000,
      "current_liabilities": 52600000000,
      "long_term_debt": 300000000,
      "income_cont_ops": 30120000000,
      "cfo": 35600000000
    },
    "2022": {
      "sales": 75760000000,
      "cogs": 14100000000,
      "receivables": 780000000,
      "current_assets": 91200000000,
      "ppe_net": 27500000000,
      "long_term_investments": 1100000000,
      "total_assets": 148900000000,
      "depreciation": 1700000000,
      "sga": 11500000000,
      "current_liabilities": 48900000000,
      "long_term_debt": 250000000,
      "income_cont_ops": 27890000000,
      "cfo": 32100000000
    }
  },
  "600036.SH": {
    "name": "招商银行",
    "2023": {
      "sales": 358900000000,
      "cogs": 98500000000,
      "receivables": 5200000000,
      "current_assets": 4580000000000,
      "ppe_net": 45600000000,
      "long_term_investments": 890000000000,
      "total_assets": 10890000000000,
      "depreciation": 3200000000,
      "sga": 89500000000,
      "current_liabilities": 8950000000000,
      "long_term_debt": 1200000000000,
      "income_cont_ops": 145600000000,
      "cfo": 156000000000
    },
    "2022": {
      "sales": 332100000000,
      "cogs": 91200000000,
      "receivables": 4800000000,
      "current_assets": 4230000000000,
      "ppe_net": 43200000000,
      "long_term_investments": 820000000000,
      "total_assets": 10120000000000,
      "depreciation": 3000000000,
      "sga": 82300000000,
      "current_liabilities": 8320000000000,
      "long_term_debt": 1100000000000,
      "income_cont_ops": 134500000000,
      "cfo": 142000000000
    }
  },
  "000002.SZ": {
    "name": "万科A",
    "2023": {
      "sales": 456700000000,
      "cogs": 358900000000,
      "r

Github ReposUpdated 1d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.