Modularity Health Evaluator
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only architecture-analysis skill that reads code structure to produce modularity guidance and shows no hidden execution, persistence, credential use, or exfiltration.
Install this only for repositories or module descriptions you want an agent to inspect for architecture and dependency analysis. Scope it to the intended project folders, and avoid exposing secrets in ordinary project files because the skill may read source and build/dependency artifacts while preparing its report.
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
64/64 vendors flagged this skill as clean.