Input Safety Guard
Security checks across malware telemetry and agentic risk
Overview
This is a coherent input-screening skill that checks user messages before answering and does not show hidden data access, persistence, or destructive behavior.
Review the default, strict, and relaxed rule profiles before installing. This skill will inspect raw user messages and may block normal prompt-security discussions unless tuned, so test it with your agent flow and make sure any host classifier or logging handles sensitive user input appropriately.
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.