Dispatching Parallel Agents
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only skill for splitting independent coding tasks across parallel agents, with no hidden code or install behavior found.
Installers should understand that this skill encourages multiple subagents to work at the same time. Use it for clearly independent tasks, give each subagent minimal necessary context, and review all returned changes before accepting or integrating them.
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
66/66 vendors flagged this skill as clean.