Claw Test Skill
Security checks across malware telemetry and agentic risk
Overview
This is a simple ClawHub test skill that only tells the agent to confirm loading and report success, with no code execution or data access.
This skill appears safe to install as a publishing-flow test. Be aware that its listing metadata includes sensitive-credential and crypto capability tags that are not reflected in the actual skill instructions, so do not treat it as a real crypto or credential-management tool.
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.