Security audit
Code Review Assistant
Security checks across malware telemetry and agentic risk
Overview
Available scanner signals did not show harmful behavior, but the actual skill artifact was not present for a full artifact-backed review.
Treat this as a low-confidence clean result: no supplied scanner signal indicates harm, but install only if you can review the actual skill files or trust the publisher/source, because the artifact was unavailable for final inspection.
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.
Static analysis
No suspicious patterns detected.