AI应用专家
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only AI adoption consulting skill with no executable behavior, hidden access, or persistence.
Installing this skill mainly adds structured guidance for AI adoption decisions. Treat its compliance, privacy, procurement, and ROI recommendations as advisory and validate sensitive business or legal decisions with qualified internal reviewers.
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
VirusTotal findings are pending for this skill version.