我的技能
Security checks across malware telemetry and agentic risk
Overview
This is a placeholder skill document with no code, install actions, data access, credentials, or persistence.
Installing this appears safe from a security standpoint, but it is only a template. Use it only if you understand it will not provide a concrete workflow until the author replaces the XXX placeholders with specific scope, inputs, outputs, and allowed actions.
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
60/60 vendors flagged this skill as clean.