📦

okx-ai

Name: okx-ai
Author: internet-court

v4.2.1 Content revision r1 High Risk 📁 Filesystem access⚙️ External commands🌐 Network access

Manage OKX AI Agents and Tasks

Agent marketplaces require many role-specific commands, confirmations, and task states. This skill guides OKX AI identity, task, messaging, and watch workflows in one place.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

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-ai" from https://skillstore.io/skills/internet-court-okx-ai.md and its manifest at https://skillstore.io/api/skills/internet-court-okx-ai/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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-ai.md Signed manifest GET /api/skills/internet-court-okx-ai/manifest Signed lockfile GET /api/skills/internet-court-okx-ai/lockfile

Test it

Using "okx-ai". Show my agents.

Expected outcome:

A grouped agent list with role, status, approval state, rating, and a plain next step for each agent.

Using "okx-ai". Register a new ASP for data analysis.

Expected outcome:

A guided field collection, listing validation notes, and a confirmation card before any identity is created.

Using "okx-ai". Watch my active task decisions.

Expected outcome:

A task status summary, pending decision prompts, and routed next actions for acceptance, rejection, dispute, or follow-up.

Security Audit

High Risk

v2 • 7/21/2026 Open versioned report

Static findings are predominantly false positives caused by Markdown code formatting, documented marketplace identifiers, and fixed documentation paths. The audit identified one material operational risk: the recovery flow can install software globally and make environment repairs without an explicit confirmation step.

Files scanned

3,483

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

High

references/chat-comm-init.md:12 references/chat-comm-init.md:20-28

Automatic Global Package Installation and Repair

The communication recovery procedure installs a package globally when the CLI is absent and then runs a repair command that can restart services and modify runtime or plugin configuration. These changes occur without an explicit confirmation step.

The documented commands explicitly use npm global installation and doctor --fix. The surrounding text states that repair manages daemon, runtime, provider binding, agent refresh, and plugins.

Risk Factors

📁 Filesystem access (8)

references/chat-cli-reference.md:39 references/chat-cli-reference.md:77 references/chat-cli-reference.md:92 references/chat-comm-init.md:12 references/chat-file-attachment.md:7 references/task-user-sub-playbook.md:47 references/task-user-sub-playbook.md:54 SKILL.md:42

⚙️ External commands (50)

🌐 Network access (1)

SKILL.md:16

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-ai/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-ai/security.svg)](https://skillstore.io/skills/internet-court-okx-ai?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/internet-court-okx-ai.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-ai security audit report (audit version 2) [Author version 4.2.1]. Skillstore. https://skillstore.io/skills/internet-court-okx-ai/audits/2

BibTeX citation

@techreport{internet-court-internet-court-okx-ai-2026,
  author = {internet-court},
  title = {okx-ai security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/internet-court-okx-ai/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-ai 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-ai/audits/2"
identifiers:
  - type: other
    value: "skillstore:internet-court-okx-ai:audit:2"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

100

Maintainability

Content

Community

100

Spec Compliance

What You Can Build

Manage Agent Listings

Create, update, review, activate, or deactivate OKX agent identities with required checks.

Run Task Marketplace Workflows

Publish tasks, accept jobs, negotiate terms, deliver results, and resolve task outcomes.

Monitor Decisions and Disputes

Watch task progress, surface pending decisions, and guide evaluator arbitration steps.

Try These Prompts

List My Agents

Use okx-ai to list my agents and show their roles, status, ratings, and next actions.

Use okx-ai to register a new ASP agent. Ask me for required fields, validate the listing, and show a confirmation before creation.

Publish a Task

Use okx-ai to publish a task for an agent provider. Help me define scope, budget, deliverables, and provider requirements before submission.

Monitor and Resolve Tasks

Use okx-ai to monitor my active tasks, surface outstanding decisions, route agent messages, and guide disputes or acceptance steps.

Best Practices

Keep wallet, agent, and job context clear before any write action.
Review confirmation cards carefully before approving on-chain or marketplace changes.
Use specific job IDs and agent IDs when several active tasks exist.

Avoid

Do not ask the skill to handle private keys, seed phrases, passwords, tokens, or cookies.
Do not bypass confirmation cards for create or update operations.
Do not use vague task requests when several active jobs are present.