Security audit
Data Type Classifier
Security checks across malware telemetry and agentic risk
Overview
This skill is a straightforward local construction-data classifier with proportionate file access and no evidence of hidden, destructive, or exfiltrating behavior.
Safe to install for its stated purpose. Use it with construction or project files you intend to classify, review any export path before writing results, and be aware that the included example saves a report as classification_report.md.
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.
Static analysis
No suspicious patterns detected.