Skills 0g-compute

📦

0g-compute

Name: 0g-compute
Author: internet-court

Content revision r1 Medium Risk ⚙️ External commands📁 Filesystem access🔑 Env variables🌐 Network access

Build 0G Compute AI Apps

0G Compute projects need exact SDK, CLI, and settlement patterns. This skill provides tested guidance for inference, fine-tuning, account funding, and provider usage.

Supports: Claude Codex Code(CC)

📊 71 Adequate

Install with my Agent

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

Agent request

Review the Skillstore skill "0g-compute" from https://skillstore.io/skills/internet-court-0g-compute.md and its manifest at https://skillstore.io/api/skills/internet-court-0g-compute/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

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-0g-compute.md Signed manifest GET /api/skills/internet-court-0g-compute/manifest Signed lockfile GET /api/skills/internet-court-0g-compute/lockfile

Test it

Using "0g-compute". Plan a 0G Compute streaming chat integration.

Expected outcome:

A setup checklist, provider selection steps, request flow, response settlement notes, and account balance checks.

Using "0g-compute". Explain how to generate images through 0G Compute.

Expected outcome:

A user-facing flow for choosing a provider, preparing a prompt, saving outputs, and settling usage.

Using "0g-compute". Prepare for a fine-tuning run.

Expected outcome:

A staged workflow covering dataset review, provider choice, task creation, monitoring, download, decryption, and security checks.

Security Audit

Medium Risk

v2 • 7/19/2026 Open versioned report

Most alerts are scanner misclassifications of Markdown, documentation links, standard installation paths, local configuration, and intended 0G examples. Two image-download fetches are confirmed because provider-supplied URLs lack destination and size controls. Financial commands also lack explicit approval guardrails.

Files scanned

4,051

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (1)

Medium

SKILL.md:42-46 SKILL.md:131-136 references/account-management.md:168-206

Financial Commands Lack Confirmation Guardrails

The skill presents token deposit, transfer, and refund commands without requiring explicit approval or rechecking the network, provider, and amount before execution.

The on-chain commands and missing approval requirement are explicit. Impact still depends on an agent having wallet access and command permissions.

Capability review items (2)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

High

references/examples/text-to-image.md:188

Fetch API call

const response = await fetch(url);

The example fetches a provider-supplied image URL without destination, redirect, response-size, or content-type controls. This permits SSRF and resource exhaustion.

High

references/examples/text-to-image.md:440

Fetch API call

const response = await fetch(imageUrl);

The example fetches a provider-supplied image URL without destination, redirect, response-size, or content-type controls. This permits SSRF and resource exhaustion.

Risk Factors

⚙️ External commands (50)

📁 Filesystem access (44)

🔑 Env variables (50)

🌐 Network access (37)

Audited by: codex 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-0g-compute/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-0g-compute/security.svg)](https://skillstore.io/skills/internet-court-0g-compute?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/internet-court-0g-compute?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/internet-court-0g-compute/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/internet-court-0g-compute.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). 0g-compute security audit report (audit version 2) [Author version unspecified]. Skillstore. https://skillstore.io/skills/internet-court-0g-compute/audits/2

BibTeX citation

@techreport{internet-court-internet-court-0g-compute-2026,
  author = {internet-court},
  title = {0g-compute security audit report (audit version 2)},
  institution = {Skillstore},
  year = {2026},
  number = {2},
  url = {https://skillstore.io/skills/internet-court-0g-compute/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: "0g-compute 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-0g-compute/audits/2"
identifiers:
  - type: other
    value: "skillstore:internet-court-0g-compute:audit:2"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Create an inference client

Generate a 0G Compute chat or image client with provider discovery and response settlement.

Operate funded provider accounts

Plan deposits, provider sub-account transfers, balance checks, and refunds for 0G Compute usage.

Run model fine-tuning

Follow the CLI workflow for dataset preparation, task creation, monitoring, download, and decryption.

Try These Prompts

Start a 0G project

Use the 0g-compute skill to outline the setup steps for a new 0G Compute testnet inference project.

Build chat inference

Use the 0g-compute skill to create a TypeScript chat inference plan with provider discovery, request headers, and processResponse.

Manage account funds

Use the 0g-compute skill to explain how to deposit, transfer funds to a provider, check balances, and request refunds.

Design a fine-tuning workflow

Use the 0g-compute skill to design a safe fine-tuning workflow with provider verification, dataset checks, task monitoring, and model download.

Best Practices

Use testnet first, then move to mainnet only after balance and provider checks pass.
Keep private keys and provider secrets in local environment storage that is never committed.
Call processResponse after each inference response to support settlement and verification.

Avoid

Do not hardcode wallet private keys, service secrets, or funded provider addresses in source files.
Do not skip provider acknowledgment, TEE checks, or balance checks before production use.
Do not upload sensitive datasets to fine-tuning providers without review and explicit approval.