Engineering
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only engineering guidance skill with safety-focused instructions and no evidence of hidden access, code execution, data collection, or persistence.
This appears safe to install from an agentic-security perspective. Because it may assist with engineering topics that can affect physical safety or legal compliance, users should verify real-world designs, code requirements, and safety-critical decisions with qualified professionals or the relevant authority.
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
66/66 vendors flagged this skill as clean.