Agent Orchestrator
Security checks across malware telemetry and agentic risk
Overview
No scanner or telemetry evidence supplied for this run shows harmful behavior, but the target artifact files were not available for independent inspection.
Because the artifact itself was not available to verify, treat this as a low-confidence clean result. Before installing, review the skill files on ClawHub for any file writes, network calls, credential use, or instructions that would run automatically outside your direct request.
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.