gstack Diagnose
Security checks across malware telemetry and agentic risk
Overview
This is a plain markdown debugging methodology skill with no executable code, dependencies, hidden persistence, or suspicious scanner signals.
This skill appears safe to install if you want a disciplined debugging workflow. It may prompt your agent to create tests, run commands, add temporary instrumentation, or build throwaway harnesses while diagnosing a bug, so review proposed changes and make sure any production instrumentation or environment access is explicitly approved.
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
56/56 vendors flagged this skill as clean.