Security audit
AI Code Review RiskRadar
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only code review skill that gives structured review guidance and does not include executable code, persistence, credential handling, or hidden behavior.
Install only if you are comfortable with an agent reviewing the relevant repository code and diffs. The scanned artifact is plain documentation with clean SkillSpector, static scan, and VirusTotal telemetry, and I found no evidence of hidden execution or data exfiltration.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.