Security audit
stack-builder
Security checks across malware telemetry and agentic risk
Overview
This skill is a transparent prompt-only workflow for designing personalized AI skill stacks, with context reading and installation steps bounded by user confirmation.
Before installing, be aware that this skill works best when it can inspect relevant project and conversation context; use it when you are comfortable with that read-only review and review any generated skills before choosing install or versioning.
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.