Architecture Research
Security checks across malware telemetry and agentic risk
Overview
This skill is a coherent architecture-research helper that reads code, gathers context, and writes diagram/report files without hidden, destructive, or credential-seeking behavior.
Install this if you want an agent to inspect repositories and produce architecture documentation. Use caution with private code, choose a dedicated output directory, and review the separate diagrams skill before allowing the SVG rendering command.
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
65/65 vendors flagged this skill as clean.