Artificial Intelligence
Security checks across malware telemetry and agentic risk
Overview
This is a small instruction-only skill that helps answer AI questions with current public information and does not request privileged access.
This skill is reasonable to install if you want AI answers to use fresher public sources. Expect the agent to browse public AI pricing, ranking, and status pages when relevant, but the skill does not request credentials, local data, or privileged system access.
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.