AI魔术教学
Security checks across malware telemetry and agentic risk
Overview
This skill is a plain magic-tutoring guide with no executable code, hidden behavior, credential use, or persistence.
This appears safe to install as a magic education skill. If you upload performance videos for feedback, only share videos you are comfortable giving to the agent and where any participants have consented.
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
63/63 vendors flagged this skill as clean.