Skills okx-agentic-wallet

📦

okx-agentic-wallet

Name: okx-agentic-wallet
Author: internet-court

v4.2.1 Content revision r1 Critical 📁 Filesystem access⚙️ External commands🌐 Network access🔑 Env variables

Operate OKX Agentic Wallet from AI

Managing on-chain wallet actions across tools is slow and error-prone. This skill routes wallet, swap, bridge, gas, strategy, portfolio, and security requests through OKX onchainos workflows.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Do not auto-install this skill.

The canonical policy requires operator review before any installation action.

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request

Review the Skillstore skill "okx-agentic-wallet" from https://skillstore.io/skills/internet-court-okx-agentic-wallet.md and its manifest at https://skillstore.io/api/skills/internet-court-okx-agentic-wallet/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/internet-court-okx-agentic-wallet.md Signed manifest GET /api/skills/internet-court-okx-agentic-wallet/manifest Signed lockfile GET /api/skills/internet-court-okx-agentic-wallet/lockfile

Test it

Using "okx-agentic-wallet". Show my wallet balances.

Expected outcome:

A concise balance summary with each chain, token symbol, user-unit amount, USD value, and abbreviated contract address.

Using "okx-agentic-wallet". Bridge 50 USDC to Optimism.

Expected outcome:

A route comparison with estimated receive amount, minimum receive amount, bridge fee, estimated time, approval need, and a confirmation prompt.

Using "okx-agentic-wallet". Is this token safe to buy?

Expected outcome:

A token risk summary with the overall risk level, triggered labels, tax information when available, and the recommended action.

Security Audit

Critical

v2 • 7/21/2026 Open versioned report

Most static matches are false positives caused by Markdown code formatting, official URLs, and explicit credential-protection guidance. The audit identified a critical trust-boundary issue: remote CLI responses can instruct the agent to run follow-up commands. The automatic installer fallback also introduces a high supply-chain risk.

Files scanned

2,177

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (2)

Critical

_shared/preflight.md:8-12 SKILL.md:54-60

Untrusted Remote Command Directives

The pre-flight workflow tells the agent to do exactly what a CLI-provided action says and to follow a backend-provided next command after confirmation. A compromised service response could direct the agent to run an unintended command or forced upgrade.

Both files explicitly instruct the agent to act on command output fields rather than using a fixed allowlist. This creates a clear remote instruction trust boundary.

High

_shared/preflight.md:14-17

Automatic Installer Download and Execution

When the CLI is absent, the fallback directs the agent to download, checksum-verify, and run an installer automatically. This expands the supply-chain attack surface without requiring a separate user confirmation.

The fallback explicitly directs automated download and execution of an installer. Checksum verification reduces but does not remove trust in the distribution channel and checksum source.

Risk Factors

📁 Filesystem access (4)

references/audit-log.md:7 references/audit-log.md:7 references/security.md:62 references/security.md:62

⚙️ External commands (21)

🌐 Network access (4)

references/gas-station.md:56 references/security-cli-reference.md:36 references/swap.md:35 SKILL.md:8

🔑 Env variables (2)

references/wallet-cli-reference.md:11 references/wallet.md:19

Audited by: claude View Audit History →

Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report

Copy report link

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

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/internet-court-okx-agentic-wallet.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Academic citations (APA · BibTeX · CFF)

APA citation

internet-court. (2026). okx-agentic-wallet security audit report (audit version 2) [Author version 4.2.1]. Skillstore. https://skillstore.io/skills/internet-court-okx-agentic-wallet/audits/2

BibTeX citation

@techreport{internet-court-internet-court-okx-agentic-wallet-2026,
  author = {internet-court},
  title = {okx-agentic-wallet security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/internet-court-okx-agentic-wallet/audits/2},
  note = {Author version 4.2.1}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "okx-agentic-wallet security audit report (audit version 2)"
version: "4.2.1"
type: report
authors:
  - name: "internet-court"
date-released: "2026-07-21"
url: "https://skillstore.io/skills/internet-court-okx-agentic-wallet/audits/2"
identifiers:
  - type: other
    value: "skillstore:internet-court-okx-agentic-wallet:audit:2"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

100

Maintainability

Content

Community

Spec Compliance

What You Can Build

Check wallet state before a transfer

Review login status, wallet address, token balances, and risk context before sending assets.

Execute a cross-chain asset move

Compare bridge routes, confirm fees and destination details, then track arrival status after broadcast.

Screen risky tokens and approvals

Run token, transaction, DApp, signature, and approval checks before interacting with unknown assets.

Try These Prompts

Check My Wallet

Check my OKX Agentic Wallet status and show my balances on Solana and Ethereum.

Send With Confirmation

Help me send 25 USDC on Solana. Show the recipient, fee information, and wait for my confirmation before sending.

Bridge And Track

Find the best route to bridge 100 USDC from Arbitrum to Base, explain fees, then track the transfer after I approve it.

Audit Before Contract Call

Before I approve this contract interaction, scan the transaction, explain any risks, and only proceed if I explicitly confirm.

Best Practices

Confirm every recipient address, chain, token, amount, fee, and route before any state-changing action.
Run the relevant security scan before contract calls, swaps, approvals, signatures, or unknown DApp interactions.
Use fresh CLI output for wallet addresses, transaction hashes, order IDs, and status checks.

Avoid

Do not pass force flags on the first attempt or bypass a risk warning without explicit user approval.
Do not ask users to paste seed phrases, private keys, session tokens, API secrets, or passwords.
Do not guess token contract addresses, bridge IDs, relayer IDs, chain names, or transaction hashes.