need
Security checks across malware telemetry and agentic risk
Overview
This is a simple instruction-only skill for clarifying vague requests and shows no evidence of hidden code, data access, persistence, or privileged behavior.
This skill is reasonable to install if you want an agent to ask clarifying questions before proposing solutions. It may ask about your goals, constraints, audience, and success criteria, so avoid sharing secrets or unnecessary sensitive personal information in those answers.
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
65/65 vendors flagged this skill as clean.