Security audit
onboard
Security checks across malware telemetry and agentic risk
Overview
This is a simple onboarding guide skill that is coherent with its purpose and does not include executable code, hidden behavior, or disproportionate access.
This skill appears safe to install for guided developer onboarding. Be aware that using it effectively may involve your agent reading the current codebase and retaining onboarding progress or answer history, but the artifact does not add executable behavior or request sensitive access by itself.
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
59/59 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.