Security audit
llm-architect
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only LLM architecture helper with no code, installer, persistence, or credential access.
Safe to install as an advisory skill. Because it may guide production LLM infrastructure decisions, review any future changes it proposes for cost, data handling, safety, and operational impact before applying them.
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
62/62 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.