← Back to Skills Marketplace
emeraldring3134-netizen

DeFi Risk Scanner

by emeraldring3134-netizen · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
153
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install defi-risk-scanner
Description
Web3/DeFi 风险扫描工具。当用户提到"分析 DeFi 协议风险"、"检查 Token 是否是 Rug Pull"、"评估项目安全性"、"查看合约风险"、"DeFi 安全"、"链上风险"、"代币风险评估"、"协议尽调"、"这个项目安全吗"时使用。覆盖主流 EVM 链，提供结构化风险评分、风险因子拆解、关键指...
README (SKILL.md)

DeFi Risk Scanner 🛡️

为 DeFi 协议和代币项目提供结构化风险评估。

⚠️ 本工具仅供教育参考，不构成财务建议。加密货币投资有极高风险，可能导致本金全损。

触发场景

用户会在以下情况下使用此技能：

  • 🔍 "帮我分析一下 [协议名] 的风险" — 输入协议名（slug），如 aave、uniswap-v3
  • 🪙 "这个代币安全吗：[地址]" — 输入合约地址，如 0x7Fc66500c84A76Ad7e9c93437bFc5Ac33E2DDaE9
  • 📊 "帮我做个协议尽调" — 全面评估 TVL、流动性、市值、合约安全
  • ⚠️ "检查这个项目是不是 Rug Pull" — 使用 Rug Pull 检测维度
  • 💰 "帮我看看这个 DeFi 能投吗" — 结合多维度给出可参与性建议

核心框架：风险评分（0-100）

评分 风险等级 说明
80-100 🟢 低风险 各项指标健康，可持续性良好
60-79 🟡 中低风险 存在少数关注点，建议深入尽调
40-59 🟠 中高风险 多个风险因子，需谨慎评估
20-39 🔴 高风险 重大风险，不建议参与
0-19 ⚫ 极高风险 高度疑似 Rug Pull 或诈骗

使用方式

协议模式（按名称查询）

# 基础用法
./scripts/risk-check.sh \x3Cprotocol-slug> [chain]

# 示例
./scripts/risk-check.sh aave ethereum
./scripts/risk-check.sh uniswap-v3 ethereum
./scripts/risk-check.sh curve-finance ethereum
./scripts/risk-check.sh lido ethereum

提示：使用协议 slug（如 aave-v3 而非 Aave V3），可通过 DeFiLlama 查找正确 slug。

代币模式（按地址查询）

# 输入合约地址（0x 开头）
./scripts/risk-check.sh 0x7Fc66500c84A76Ad7e9c93437bFc5Ac33E2DDaE9 ethereum
./scripts/risk-check.sh 0x1f9840a85d5aF5bf1D1762F925BDADdC4201F984 ethereum

分析维度

协议模式（DefiLlama 数据源）

  1. TVL（总锁仓量） — 最大权重因子

    • $1B = 高度可信 ✅

    • $100M-$1B = 良好 ✅
    • $10M-$100M = 中等 ⚠️
    • \x3C$10M = 低流动性 ⚠️

  2. 链上多样性 — 覆盖链数量

    • ≥5 条链 = 多链部署 ✅
    • 2-4 条链 = 部分多链 ⚠️
    • 单链 = 集中风险

  3. 协议识别 — 知名协议加分

    • Aave、Uniswap、Curve、Compound、Maker、Synthetix = +10分
    • Lido = +8分

  4. 质押/Pool2 — 健康度指标

代币模式（DexScreener 数据源）

  1. 流动性 vs 市值比 — 最关键指标

    • ≥10% = 流动性充足 ✅（+20分）
    • 5-10% = 中等 ⚠️（+10分）
    • 1-5% = 低 ⚠️（0分）
    • \x3C1% = 🔴 极高风险（-20分）

  2. 市值/FDV 比 — 代币解锁风险

    • ≥80% = 流通量健康 ✅（+20分）
    • 50-80% = 部分未释放 ⚠️（+10分）
    • 20-50% = 大量未解锁 ⚠️
    • \x3C20% = 🔴 大量代币未解锁（-15分）

  3. 交易活跃度 — 24h 成交量/流动性比

    • ≥5% = 活跃市场 ✅（+10分）
    • 1-5% = 一般活跃 ⚠️（+5分）

  4. DEX 分布 — 交易对数量

    • ≥3 个交易所 = 分散风险 ✅
    • 仅 1 个 = 集中风险 ⚠️

输出示例

═══════════════════════════════════════════════════
  🔍 DeFi Risk Scanner - 风险评估报告
═══════════════════════════════════════════════════
  目标: aave
  链:   ethereum
───────────────────────────────────────────────────

▶ 📊 DefiLlama 链上数据
  ─────────────────────────────────
  名称:         Aave
  符号:         AAVE
  官网:         https://aave.com
  Twitter:      @aave
  描述:         Aave is an Open Source...
  TVL:          $59.93B USD

  风险评分计算...
  ─────────────────────────────────
  综合评分:     100/100 🟢 低风险 | 安全
  ─────────────────────────────────

  风险因子拆解:
    ✅ TVL > $1B — 高度可信
    ✅ 多链部署（25 条链）— 分散风险
    ✅ 有质押池（$325.50M）
    ✅ 知名协议，长期运营

▶ 🔐 安全与审计建议
  推荐验证步骤:
    1. 在 https://debank.com/ 查看钱包持仓分布
    2. 在 https://tokensniffer.com/ 分析代币合约风险
    3. 在 https://revoke.cash/ 检查授权风险

═══════════════════════════════════════════════════
  综合风险评分: 100/100 🟢 低风险 | 安全
═══════════════════════════════════════════════════
  ✅ 结论: 该项目各项指标健康，可持续性良好
  💡 建议: 可进行常规参与，建议持续监控

⚠️ 免责声明: 以上分析仅供参考，非财务建议。
  DYOR（Do Your Own Research）

数据源

用途 API 费用
协议 TVL/基本信息 api.llama.fi/protocol/{slug} 免费
代币流动性/市值 api.dexscreener.com 免费
合约源码验证 Etherscan API 免费 Key
代币分析 tokensniffer.com 免费

推荐验证工具

  • 链上数据: Etherscan / Polygonscan / Arbiscan
  • DeFi 聚合: DeFiLlama / DeBank / DappRadar
  • 安全审计: Immunefi / Hacken / Trail of Bits
  • 代币分析: Token Terminal / CoinGecko / DexScreener
  • 授权管理: revoke.cash / approval.sh

与其他技能的区别

  • vs crypto-watcher: 监控钱包余额变化，本技能专注于协议/代币风险评分
  • vs portfolio-risk-analyzer: 聚焦于单协议的深度安全评估，非组合分析
  • 核心优势: 完全免费、无需 API Key、实时链上数据

定价策略（路线图）

功能 免费版 Pro 版（规划中）
基础 TVL 查询 ✅ ✅
合约验证状态 ✅ ✅
流动性/市值分析 ✅ ✅
Rug Pull 评分 ❌ ✅
实时预警 ❌ ✅
历史风险追踪 ❌ ✅
PDF 报告导出 ❌ ✅

风险评估原则

  1. 数据优先: 优先使用链上数据，其次才是项目自述
  2. 多源交叉: 单个异常 ≠ 诈骗，多个叠加 = 高风险
  3. 保守原则: 无法确认安全时，默认给出警告评分
  4. 坦诚局限: 明确告知无法100%确认安全的场景
  5. DYOR 提醒: 始终强调用户需自行验证
Usage Guidance
This skill appears to do what it claims, but check these before installing or running: - Inspect and run the script locally rather than allowing automatic execution by an agent: it is a Bash script that calls public APIs and computes scores, so executing it locally is straightforward and safer. - Install required CLI tools: the README and script require bash, curl, jq, awk, and bc. The registry metadata did not declare these dependencies—make sure you have them. - The script makes outbound network calls to public DeFi APIs (api.llama.fi, api.dexscreener.com, etc.). If you are in a restricted environment, be aware of those network requests. - No credentials are requested by the skill, and it does not appear to exfiltrate local files or secrets. Never provide private keys, seed phrases, or other sensitive secrets when using the tool (not required for its operation). - Source/homepage/owner appear minimal; if you need higher assurance, ask the publisher for provenance (GitHub repo, maintainer identity) or run the script in an isolated environment first. - Remember outputs are informational only and not financial advice (SKILL.md already states this). Do your own research before acting on any recommendations.
Capability Analysis
Type: OpenClaw Skill Name: defi-risk-scanner Version: 1.0.0 The bundle provides a legitimate DeFi risk assessment tool that fetches data from public APIs (DefiLlama and DexScreener) to calculate risk scores for protocols and tokens. The core logic in `scripts/risk-check.sh` uses standard tools like `curl`, `jq`, and `awk` to analyze TVL, liquidity, and market cap without any evidence of data exfiltration, persistence, or malicious execution. While the script contains an unused function `score_for` that utilizes `eval`, there is no evidence of intentional exploitation or harmful behavior.
Capability Assessment
ℹ Purpose & Capability
The name/description match the behavior: the script fetches protocol or token data from public DeFi APIs and computes scores. Minor mismatch: the registry lists no required binaries, but README/SKILL.md and the script itself require common CLI tools (bash, curl, jq, awk, bc). This is a documentation/inventory inconsistency rather than a functional mismatch.
✓ Instruction Scope
SKILL.md and the script instruct the agent/user to call public APIs and run the included script. The runtime instructions do not tell the agent to read local secrets, other skills' configs, or arbitrary files. All network calls in the script target known public DeFi services (api.llama.fi, api.dexscreener.com); references in docs to other services (Etherscan, Token Sniffer, RugCheck) are expected and not used in a way that requests secrets.
✓ Install Mechanism
No install spec is provided (instruction-only with a shipped script), so nothing is downloaded or executed from external arbitrary URLs during install. The only shipped executable is a local shell script; there is no installer that pulls remote code.
✓ Credentials
The skill declares no required environment variables or credentials, and the script uses public, unauthenticated API endpoints. No secrets (API keys, tokens, passwords) are requested. Docs mention some services that may optionally require keys (e.g., Etherscan), but the skill does not demand them.
✓ Persistence & Privilege
always is false and user-invocable is true. The skill does not request permanent presence, modify other skills, or require elevated agent/system privileges.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install defi-risk-scanner
  3. After installation, invoke the skill by name or use /defi-risk-scanner
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release - 5-dimension DeFi risk scoring framework. TVL analysis via DefiLlama + token liquidity via DexScreener. Risk score 0-100 with actionable recommendations.
Metadata
Slug defi-risk-scanner
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is DeFi Risk Scanner?

Web3/DeFi 风险扫描工具。当用户提到"分析 DeFi 协议风险"、"检查 Token 是否是 Rug Pull"、"评估项目安全性"、"查看合约风险"、"DeFi 安全"、"链上风险"、"代币风险评估"、"协议尽调"、"这个项目安全吗"时使用。覆盖主流 EVM 链，提供结构化风险评分、风险因子拆解、关键指... It is an AI Agent Skill for Claude Code / OpenClaw, with 153 downloads so far.

How do I install DeFi Risk Scanner?

Run "/install defi-risk-scanner" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is DeFi Risk Scanner free?

Yes, DeFi Risk Scanner is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does DeFi Risk Scanner support?

DeFi Risk Scanner is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created DeFi Risk Scanner?

It is built and maintained by emeraldring3134-netizen (@emeraldring3134-netizen); the current version is v1.0.0.

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463815 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259802 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200680 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 Comments