Replit Agent
Security checks across malware telemetry and agentic risk
Overview
This is a non-executable Replit guidance skill whose deployment and database topics fit its stated purpose.
Safe to install as general Replit guidance. Before deploying anything publicly, review generated code, database/auth setup, secret configuration, and whether test or real user data is being used.
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.