Openclaw Free Models

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:20 PM UTC
• Version:
  1.0.0

Overview

This skill is a plain setup guide for configuring free or low-cost AI model providers, with expected but sensitive API-key handling that users should treat carefully.

Install only if you are comfortable configuring third-party AI provider accounts in OpenClaw. Use your own API keys, verify free-tier and pricing terms directly with each provider, do not share keys with the listed support contacts, and rotate any key that may have been exposed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The skill repeatedly instructs users to place API keys directly into persistent OpenClaw configuration without any warning about credential sensitivity, secure storage, shell history exposure, or host compromise risk. While this is common setup guidance, omitting basic secret-handling precautions can lead to credential leakage through shared machines, backups, screenshots, or plaintext config files.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The balance-check examples send bearer tokens to third-party endpoints but provide no warning that the commands transmit live credentials and may expose them via shell history, process inspection, logs, or copy-paste mistakes. The requests themselves are expected for the feature, but the missing security guidance increases the chance of accidental credential disclosure.

VirusTotal

64/64 vendors flagged this skill as clean.