Architecture Governance
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent architecture governance and reporting aid, with only an optional local report script and no evidence of hidden or unsafe behavior.
Review the optional Python helper before running it, choose report output paths deliberately, and only adapt the metric collection examples for internal systems where you have authorization and least-privilege credentials.
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.