mnemo-memory

Security checks across malware telemetry and agentic risk

Overview

This is a clearly disclosed cloud memory skill, but users should treat stored memories and database credentials as sensitive.

Install only if you want agent memories stored in a cloud-backed database and potentially shared across configured agents or teammates. Do not store secrets, regulated data, or private source material unless you have approved that use; use dedicated TiDB credentials, protect the config, and review who can access or delete memories.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (2)

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill explicitly promotes cloud-persistent, cross-session, and multi-agent shared memory but does not warn users that prompts, code, secrets, or personal data may be retained in a third-party cloud database and become accessible across agents or teammates. In an agent-memory context, users may unintentionally store sensitive material, so the omission increases the risk of privacy leakage, over-retention, and inappropriate data sharing.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The setup examples instruct users to place database host, username, and password directly into configuration without any warning about secret management. This can lead to credential exposure through checked-in config files, logs, screenshots, or shared plugin settings, potentially granting unauthorized access to the backing TiDB instance and all stored agent memory.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal