Skill Manager
Security checks across malware telemetry and agentic risk
Overview
This is a short guide for installing OpenClaw skills, with normal third-party install risk but no hidden code or malicious behavior in the artifact.
Treat the commands as examples, not something to run blindly. Install only skills and npm packages from maintainers you trust, inspect a target skill’s SKILL.md and setup scripts before installing, and provide API keys only to integrations you intentionally choose to use.
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
63/63 vendors flagged this skill as clean.