Security audit
Content Intake Triage
Security checks across malware telemetry and agentic risk
Overview
This is a narrow content-triage prompt skill with no code execution, credential access, private file reading, or network behavior.
This appears safe to install for simple controlled content-triage examples. It is very limited and may be useful mainly for validation or demonstration workflows rather than broad content review.
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.