Agent Memory Systems (Alex)
Security checks across malware telemetry and agentic risk
Overview
This is a guidance-only skill about designing agent memory systems, with no code, installers, credential use, persistence, or hidden actions found.
This skill appears safe to install as an advisory prompt for memory-system design. It does not implement storage or connect to databases; review any separate connector or memory-writing skill before granting access to private documents, vector stores, or credentials.
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.