Security audit
Superpowers Dispatching Parallel Agents
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only skill that teaches users how to split independent work across parallel agents, with no hidden code or credential access found.
This skill is reasonable to install if you want guidance for delegating independent coding tasks to multiple agents. When using it, give each subagent only the necessary context, keep tasks non-overlapping, review returned changes, and run tests before integrating work.
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.
Static analysis
No suspicious patterns detected.