Memori
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed long-term memory integration that stores agent history remotely only after the user configures Memori credentials.
Install only if you are comfortable with agent conversations, tool traces, workflow history, and decisions being sent to Memori and stored as long-term memory. Use scoped credentials and a dedicated project ID, avoid sharing secrets while enabled, and confirm how to pause, clear, or delete stored memories in Memori.
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.