Multi-Agent Parallel Build
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill for coordinating parallel coding agents, with the main risk being normal user-approved file changes by spawned agents.
Install only if you want an agent to help coordinate multi-agent coding work. Keep spawned agents confined to separate files or working directories, review generated prompts and sed commands before running them, and do not include secrets or sensitive internal API data in shared agent instructions.
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.