Model Config
Security checks across malware telemetry and agentic risk
Overview
This skill is a documentation-style guide for configuring OpenClaw model providers and sessions, with no executable payloads or hidden behavior found.
Before installing, understand that this skill may guide an agent through changing OpenClaw model configuration, cron model pins, and provider settings. Use it only where the agent is allowed to inspect or edit OpenClaw config and handle provider API keys.
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.