Ask
Security checks across malware telemetry and agentic risk
Overview
This is a simple question-framing skill that only changes conversational behavior and does not request code execution, data access, credentials, or persistence.
This skill appears safe to install based on the artifacts. It may make the assistant respond by asking structured follow-up questions before giving advice, so install it if you want that thinking-partner style for decisions and problem exploration.
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.