Model Migration

Security checks across malware telemetry and agentic risk

Overview

This is a coherent OpenClaw model-migration guide, with expected configuration changes but some operational cautions around API keys and installer commands.

Before using it, back up ~/.openclaw/openclaw.json, prefer the interactive auth login flow instead of putting API keys directly in shell commands, and review any remote installer script before running it. Expect the skill to change OpenClaw's configured provider/model and restart the OpenClaw gateway.

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 (1)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill instructs the agent/user to run multiple shell commands that modify authentication, model configuration, and service state, including non-interactive onboarding with secret-bearing CLI flags and gateway restarts, without any explicit warning, confirmation, or rollback guidance. In an agent setting, this can cause unintended reconfiguration, service disruption, or credential exposure in shell history/logs if executed automatically or copied blindly.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal