memory-stack-gungun - AI 记忆栈
Security checks across malware telemetry and agentic risk
Overview
This skill is a static guide for designing an AI memory system and does not contain executable code or hidden installation behavior.
Before installing, understand that the skill encourages building persistent memory stores that may contain preferences, conversation history, and private knowledge. Use it with a trusted workspace, avoid indexing secrets or sensitive files unnecessarily, and keep any vector database or memory directory under your control.
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
66/66 vendors flagged this skill as clean.