AI Dev Workflow
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only AI coding workflow skill with no executable installer, hidden access, or autonomous behavior.
Safe to install as a planning and code-generation workflow. Review generated app code before real deployment, especially sharing links, uploads, notifications, deployment files, and privacy-sensitive features; state your preferred technology stack if you do not want the default example stack.
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
VirusTotal findings are pending for this skill version.