ClawHub
Back to skill

Security audit

0G Compute

Security checks across malware telemetry and agentic risk

Overview

This is a coherent 0G Compute integration, but users should handle wallet keys, on-chain funds, and provider API secrets carefully.

Install only if you are comfortable trusting the external 0G CLI package. Use a dedicated low-balance wallet, protect ~/.0g-compute-cli/config.json and openclaw.json, do not share provider API secrets, verify providers before use, and manually confirm any deposit, transfer, retrieve, or refund command.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The CLI reference shows a provider API secret in example output (`API Secret: sk-abc123...`) and immediately instructs users to use it as an `apiKey`, but it does not warn that this value is sensitive and must never be logged, shared, or committed. In a wallet- and provider-management skill, normalizing display of secrets increases the chance users expose credentials in screenshots, terminal logs, chat transcripts, or automation output, which could let others consume paid inference services or impersonate the user to that provider.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The guide tells users to retrieve a provider secret and place it directly into `openclaw.json`, but it does not warn that this value is a credential, should be treated as sensitive, or should not be committed to source control, logs, screenshots, or shared configs. In this context, that omission can lead to credential leakage and unauthorized use of the provider-backed account or inference access, especially because the secret is tied to a funded on-chain sub-account.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.