token-scan

by certik-ai

Scan token contract security risk and return a structured summary including score, tax, holder concentration, and LP lock status. Supported chains are bsc, eth, solana, arbitrum, base, polygon, avax, tron, ton, plasma, and sui. Trigger when the user provides a chain and contract address and asks for token risk analysis, security review, high-risk item identification, tax interpretation, or holder distribution analysis.

3.7k安全与合规未扫描2026年3月23日

安装

claude skill add --url github.com/openclaw/skills/tree/main/skills/certik-ai/token-scan

文档

Token Scan

Use {skillDir}/scripts/token_scan.py to inspect one token contract with the CertiK token scan API.

Use this skill when the user wants a token risk review for a specific chain and contract address.

When to use this skill

  • Analyze token contract security risk
  • Review high-risk findings and alert severity
  • Interpret buy or sell tax fields
  • Check holder concentration and LP lock status

Supported chains

bsc, eth, solana, arbitrum, base, polygon, avax, tron, ton, plasma, sui

If the user provides a chain outside this list, do not call the API. Tell the user the chain is not supported yet and list the supported chains.

Workflow

  1. Confirm the chain is supported.
  2. Validate the address format when the chain format is obvious from the input.
  3. Prefer the bundled Python script for execution.
  4. If Python is unavailable, use the documented curl fallback.
  5. If the result is still running, report that the scan is in progress instead of pretending the scan is complete.
  6. Return the result in this order:
    • risk overview
    • alert list
    • additional token signals such as tax, holder concentration, and LP lock
  7. Only include raw fields when the user explicitly asks for audit-level detail.

Execution

Important: --chain only supports bsc|eth|solana|arbitrum|base|polygon|avax|tron|ton|plasma|sui. If the user provides a chain outside this list, do not call the API. Reply that the chain is not supported yet and include the supported chain list so the user can switch.

Prefer Python first:

bash
python3 scripts/token_scan.py --chain "bsc" --contract "0x..."

If Python is unavailable, use curl:

bash
curl -sG "https://open.api.certik.com/token-scan" \
  -H "Accept: application/json, text/plain, */*" \
  --data-urlencode "chain=bsc" \
  --data-urlencode "address=0x..."

Output requirements

  1. Risk overview must include score, alert_count, and the highest alert level.
  2. Alert list must be sorted by Critical -> Major -> Medium -> Minor and show up to 8 items.
  3. If alert_count > 8, explicitly say: Total N alerts, showing the top 8 highest-priority items.
  4. Clarify that values like skyknight_score.details.buy_tax and skyknight_score.details.sell_tax are deduction factors, not the real tax percentage.
  5. Prefer the real buy or sell tax value from security_summary.*.extended_data.* when it exists.

Public API

  • Endpoint: GET https://open.api.certik.com/token-scan
  • Query parameters:
    • chain (required)
    • address (required)

Example:

bash
curl -sG "https://open.api.certik.com/token-scan" \
  -H "Accept: application/json, text/plain, */*" \
  --data-urlencode "chain=eth" \
  --data-urlencode "address=0x1f9840a85d5aF5bf1D1762F925BDADdC4201F984"

Supported chain formats:

  • arbitrum: EVM hex 0x... with 42 chars
  • avax: EVM hex 0x... with 42 chars
  • base: EVM hex 0x... with 42 chars
  • bsc: EVM hex 0x... with 42 chars
  • eth: EVM hex 0x... with 42 chars
  • plasma: EVM hex 0x... with 42 chars
  • polygon: EVM hex 0x... with 42 chars
  • solana: Base58 public key
  • sui: Hex 0x... with module path
  • ton: EQ or UQ prefix, 46-48 chars
  • tron: Base58check, starts with T, 34 chars

Result notes

  • If message is in progress, the scan has not finished.
  • If message is success, the scan is complete and can be summarized.
  • If message is error, return the upstream error information.
  • skyknight_score.details.buy_tax and skyknight_score.details.sell_tax are deduction factors, not literal tax percentages.
  • Prefer actual tax values from:
    • security_summary.buy_tax.extended_data.buy_tax
    • security_summary.sell_tax.extended_data.sell_tax

相关 Skills

安全专家

by alirezarezvani

Universal
热门

覆盖威胁建模、漏洞评估、安全架构设计、代码审计与渗透测试,内置 STRIDE、OWASP、加密模式和安全扫描流程,适合系统设计评审与上线前安全排查。

安全专家把威胁建模、漏洞分析到渗透测试串成一套流程,内置 STRIDE 与 OWASP 指南,做安全设计和排查更省心。

安全与合规
未扫描9.0k

安全运营

by alirezarezvani

Universal
热门

覆盖应用安全、漏洞管理与合规审计,支持代码/依赖扫描、CVE 评估、Secrets 检测和安全自动化,适合做安全基线落地、漏洞响应、审计检查与安全开发治理。

应用安全、漏洞管理和合规检查一套打通,还能自动化扫描与响应,帮团队更早发现并收敛风险。

安全与合规
未扫描9.0k

安全审计

by alirezarezvani

Universal
热门

安装前审计 Claude Code Skill 的代码执行、Prompt 注入和依赖供应链风险,支持本地目录或 Git 仓库扫描,输出 PASS/WARN/FAIL 结论及修复建议

把代码审查、漏洞扫描和合规检查串成一条线,帮团队更早发现风险,做安全治理更省心。

安全与合规
未扫描9.0k

相关 MCP 服务

搜索和分析 Sentry 错误报告,辅助调试。

把零散的 Sentry 错误报告变成可检索线索,帮你在海量报错里更快定位线上故障,排障调试明显省时。

安全与合规
616

为 AI agents 提供安全层:拦截 prompt injection、识别伪造 packages,并扫描漏洞风险。

给 AI Agent 补上关键安全层,能拦截 prompt 注入、识别伪造包并扫描漏洞风险,把防护前置更省心。

安全与合规
92

强化安全性的 NotebookLM MCP,集成 post-quantum encryption,提升数据防护能力。

安全与合规
47

评论