model-troubleshooter
Security checks across malware telemetry and agentic risk
Overview
This is a plain troubleshooting guide for OpenClaw model issues, with disclosed local log/config actions and no evidence of hidden code or data exfiltration.
Before installing, understand that the skill may guide your agent to inspect OpenClaw logs, restart the gateway, change model settings, and update API-key configuration. Confirm those changes before applying them, adapt the hard-coded Windows log path if needed, and never paste real API keys into chat or logs.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- 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
VirusTotal
64/64 vendors flagged this skill as clean.