Init Program
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent project-initialization helper that creates agent instruction files and scaffolds project files with user confirmation for important choices.
Before installing, expect this skill to create or update AGENTS.md or CLAUDE.md and potentially scaffold project files or run validation/setup commands. Review the proposed stack, instruction-file language, generated files, and any dependency or generator commands before allowing changes in an important repository.
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.
