Security audit
agent-org-chart
Security checks across malware telemetry and agentic risk
Overview
This is a design-only skill for planning multi-agent team structure and does not contain executable code or hidden installation behavior.
Installers should treat this as low-risk planning guidance. The main thing to review is whether any org chart you later create from it gives agents broad write access, memory, or third-party tool authority without the human gates and caps the skill recommends.
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.
Static analysis
No suspicious patterns detected.