技能 AgentLink Skill
📦

AgentLink Skill

內容修訂 r1 高風險

使用 AgentLink 驗證代理身分

AI 代理需要可信任的身分，合作夥伴服務才能驗證它們。AgentLink 提供在 Base 上進行設定、生物特徵映射、註冊表檢查及簽署請求標頭的指引。

支援: Claude Codex Code(CC)
Maintain this Skill? Claim it ⚠️ 38 差

使用我的智慧代理安裝

將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。

智能體請求
Review the Skillstore skill "AgentLink Skill" from https://skillstore.io/skills/internet-court-humanode-agentlink.md and its manifest at https://skillstore.io/api/skills/internet-court-humanode-agentlink/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。

Agent 可讀資源

當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。

Markdown 詳情 GET /skills/internet-court-humanode-agentlink.md 已簽名 manifest GET /api/skills/internet-court-humanode-agentlink/manifest 已簽名 lockfile GET /api/skills/internet-court-humanode-agentlink/lockfile

測試它

正在使用「AgentLink Skill」。 我需要確認我的代理是否已準備好使用 AgentLink。

預期結果:

  • 確認人類擁有者已完成生物特徵映射，並將其橋接至 Base。
  • 為擁有者地址產生 Linker URL，並請擁有者簽署。
  • 在使用合作夥伴端點之前，確認註冊表狀態同時顯示為已連結且有效。

正在使用「AgentLink Skill」。 我想在不暴露金鑰的情況下整合請求簽署。

預期結果:

  • 當金鑰儲存在 KMS、HSM 或祕密管理工具中時，請使用外部簽署器。
  • 將代理公開地址和簽署回呼函式傳遞給 AgentLink 用戶端。
  • 記錄請求結果時，不要記錄私鑰、簽章或已簽署標頭。

正在使用「AgentLink Skill」。 我想呼叫免費增值合作夥伴端點。

預期結果:

回應應識別端點、確認所需的 AgentLink 標頭、檢查有效的註冊表狀態，並說明簽章遭拒時的重試處理方式。

安全審計

高風險
v2 • 2026/7/19 開啟版本化報告

The Markdown backtick and reconnaissance alerts are false positives. Genuine risks include raw wallet-key handling, unpinned npm execution, signed third-party requests, and an endpoint advertising coordinated X activity.

1
已掃描檔案
181
分析行數
12
複核項目
0
已忽略的誤報

已確認的安全問題 (7)

高
SKILL.md:26
Crypto seed/private key mention
Run the CLI with `npx` (no global install needed) and store your agent private key. No on-chain writ
The workflow asks users to store an agent private key through an npm CLI. Package or host compromise could disclose a wallet signing credential.
高
SKILL.md:29
Crypto seed/private key mention
# Store the agent private key in the encrypted local keystore.
The CLI receives a private key before placing it in an encrypted keystore. Security depends on the package and local host remaining trustworthy.
高
SKILL.md:86
Crypto seed/private key mention
**Option A — raw private key.** Simplest for a self-hosted agent that keeps its key in an environmen
The guide explicitly offers a raw private-key integration. Exposure would allow unauthorized request signatures and potentially wallet operations.
高
SKILL.md:93
Crypto seed/private key mention
privateKey: process.env.AGENT_PRIVATE_KEY as `0x${string}`,
The example passes a raw wallet private key into SDK code. This is a genuine high-impact secret-handling operation.
高
SKILL.md:126
Crypto seed/private key mention
privateKey: process.env.AGENT_PRIVATE_KEY as `0x${string}`,
The header builder receives the raw wallet private key. Dependency compromise or accidental logging could expose it.
高
SKILL.md:26-37SKILL.md:78-93
Unpinned Package Handles Wallet Private Key
The guide runs unpinned npm packages and supplies an agent private key to them. A compromised release could steal the key.
The documented npx and npm commands omit versions, and the same workflow gives the installed software a wallet private key.
中
SKILL.md:163-170
Coordinated Social Platform Activity
The advertised WURK endpoint can commission an X raid. This can enable coordinated platform manipulation without consent controls.
The skill explicitly describes the endpoint as commissioning an X raid, and no safeguards or consent requirements are stated.
能力複核項目 (12)

這些是真實的本機能力，對此技能而言可能是預期行為，因此需要複核，但不會按已確認的惡意行為計分。

高
SKILL.md:93
Generic API/secret keys
privateKey: process.env.AGENT_PRIVATE_KEY as `0x${string}`,
A raw wallet private key is passed from the environment into a third-party SDK. Compromise could enable unauthorized signatures and wallet actions.
高
SKILL.md:126
Generic API/secret keys
privateKey: process.env.AGENT_PRIVATE_KEY as `0x${string}`,
The SDK receives the raw private key to build authentication headers. Dependency or process compromise could expose the signing credential.
低
SKILL.md:111
Hardcoded URL
const response = await agentFetch('https://api.xona-agent.com/base-main/image/nano-banana', {
The example sends a signed HTTPS POST to an external XONA service. This exposes authentication metadata and request content to that operator.
低
SKILL.md:143
Hardcoded URL
agentlink request https://api.xona-agent.com/base-main/image/nano-banana --network base
The CLI command sends a signed agentlink header to the external XONA domain. Users must trust that service with authentication metadata.
低
SKILL.md:158
Hardcoded URL
| `POST https://api.xona-agent.com/base-main/video/short-generation` | Generate a short video from a
The skill advertises an external XONA video endpoint that receives signed requests and user prompts. That creates a third-party trust boundary.
低
SKILL.md:159
Hardcoded URL
| `POST https://api.xona-agent.com/base-main/image/nano-banana` | Generate an image from a text prom
The external XONA image endpoint receives signed authentication and prompt data. Its operation depends on an unaudited third party.
低
SKILL.md:169
Hardcoded URL
| `GET https://wurkapi.fun/base/agentlink/xraid/xverified/small` | Commission an X (Twitter) raid |
The skill advertises a WURK endpoint for commissioning X activity. Use sends authentication to an external operator.
低
SKILL.md:170
Hardcoded URL
| `GET https://wurkapi.fun/base/agentlink/agenttohuman` | Commission an agent-to-human job |
The agent-to-human job endpoint is operated by an external WURK domain. Signed use creates an explicit third-party trust boundary.
低
SKILL.md:93
Environment variable access (dot notation)
privateKey: process.env.AGENT_PRIVATE_KEY as `0x${string}`,
The example reads AGENT_PRIVATE_KEY from the process environment. This is intentional credential access with meaningful exposure if dependencies or logs are compromised.
低
SKILL.md:126
Environment variable access (dot notation)
privateKey: process.env.AGENT_PRIVATE_KEY as `0x${string}`,
The header-building example reads the wallet private key from process.env. Any code in the process can potentially access the same secret.
低
SKILL.md:93
Environment variable object
privateKey: process.env.AGENT_PRIVATE_KEY as `0x${string}`,
The code directly accesses the process environment to obtain a signing key. The operation is legitimate but security-sensitive.
低
SKILL.md:126
Environment variable object
privateKey: process.env.AGENT_PRIVATE_KEY as `0x${string}`,
The code directly accesses process.env for a wallet credential. This creates real secret-exposure risk within the application process.
審計單位: codex 檢視審計紀錄 →
分享與引用此報告

分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。

開啟版本化報告
安全評估

複製報告連結

https://skillstore.io/skills/internet-court-humanode-agentlink/audits/2?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown 徽章

[![Skillstore security assessment](https://skillstore.io/badges/skills/internet-court-humanode-agentlink/security.svg)](https://skillstore.io/skills/internet-court-humanode-agentlink?utm_source=security_passport_badge)

HTML 徽章

<a href="https://skillstore.io/skills/internet-court-humanode-agentlink?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/internet-court-humanode-agentlink/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

嵌入卡片

<iframe src="https://skillstore.io/embed/skills/internet-court-humanode-agentlink.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
學術引用 (APA · BibTeX · CFF)

APA 引用

internet-court. (2026). AgentLink Skill security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/internet-court-humanode-agentlink/audits/2

BibTeX 引用

@techreport{internet-court-internet-court-humanode-agentlink-2026, author = {internet-court}, title = {AgentLink Skill security audit report (audit version 2)}, institution = {Skillstore}, year = {2026}, number = {2}, url = {https://skillstore.io/skills/internet-court-humanode-agentlink/audits/2}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "AgentLink Skill security audit report (audit version 2)" version: "unspecified" type: report authors: - name: "internet-court" date-released: "2026-07-19" url: "https://skillstore.io/skills/internet-court-humanode-agentlink/audits/2" identifiers: - type: other value: "skillstore:internet-court-humanode-agentlink:audit:2" description: "Skillstore immutable audit report identifier"

Skillstore 評分

評分依據 證據置信度: 中
55
架構
85
可維護性
87
內容
65
社群
65
規範符合度

你可以打造什麼

準備已驗證的代理錢包

設定 AI 代理在註冊表中顯示為已連結且有效之前所需的步驟。

審查身分與簽署流程

檢查人類擁有者、代理錢包、註冊表狀態及已簽署請求標頭如何協同運作。

規劃免費增值端點存取

整理哪些合作夥伴端點需要 AgentLink 標頭，以及應優先執行哪些作業檢查。

試試這些提示

檢查設定就緒狀態 
協助我準備使用 AgentLink。我有一個代理錢包，需要將它連結至 Base 上已完成生物特徵映射之擁有者的步驟。
建立連結檢查清單 
建立一份檢查清單，用於為擁有者地址 {owner_address} 產生 AgentLink Linker URL，並確認有效的註冊表狀態。
選擇簽署方式 
比較我的代理使用原始私鑰簽署與外部簽署器整合的差異。針對此部署情境建議較安全的選項：{deployment_context}。
規劃端點整合 
建立使用 AgentLink 已簽署標頭呼叫 {partner_endpoint} 的實作計畫。包含驗證、祕密處理及失敗處理。

最佳實務

  • 當正式環境金鑰必須保留在程序之外時，請使用外部簽署器或祕密管理工具。
  • 將已簽署請求傳送至合作夥伴端點之前，請驗證註冊表中的已連結和有效狀態。
  • 避免在日誌和共用提示中包含已簽署標頭、私鑰及擁有者錢包詳細資料。

避免

  • 將代理私鑰或已簽署標頭提交至原始碼版本控制系統。
  • 假設擁有者不再符合生物特徵映射要求後，代理仍會維持有效狀態。
  • 將 AgentLink 已簽署標頭傳送至不需要或不信任 AgentLink 的端點。

常見問題

AgentLink 會驗證什麼？
它會將代理錢包連結至已完成生物特徵映射的人類擁有者，並允許服務驗證已簽署的代理請求。
代理可以獨自完成生物特徵映射嗎？
不行。人類擁有者必須完成生物特徵映射並簽署連結交易。
此技能著重於哪個網路？
本指南著重於 Base 主網及該網路的 AgentLink 註冊表設定檔。
此技能是否提供可執行程式碼？
不會。這是一份說明 CLI 命令、SDK 使用方式及端點需求的 Markdown 指南。
應如何處理私鑰？
請盡可能使用祕密管理工具或外部簽署器，且絕不要記錄或提交私鑰。
Claude、Codex 或 Claude Code 可以使用此技能嗎？
可以。報告將此技能標示為與 Claude、Codex 及 Claude Code 相容。

開發者詳細資訊

授權

MIT

Skillstore 修訂

r1

版本提示

作者未聲明版本。

儲存庫

https://github.com/internet-court/internet-court-skill/tree/main/vendored/humanode/humanode-agentlink

引用

3f6e026a3363e0954ede7bef0cfe88d4475de137

維護新鮮度

2026/7/18

使用量

1 次下載 · 0 次瀏覽

檔案結構

📄 SKILL.md

internet-court 的更多技能

查看全部

相關技能

查看全部