Memory Pro System

• Outcome: Review
• Latest audit: May 29, 2026, 9:28 PM
• Version:
  0.0.7

Overview

This appears to be a legitimate memory assistant, but it needs Review because it persistently stores user content and may process it with third-party LLMs without clear privacy controls.

Review before installing. Do not store secrets, regulated data, confidential business notes, or sensitive personal information unless you are comfortable with long-term local retention, daily log files, background processing, and possible third-party LLM processing. Check the cloned repository and configure API keys, Telegram push, retention, and deletion behavior deliberately.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill explicitly positions itself as a memory system and later states that all content is written to persistent stores and daily log files, but the user-facing description and usage guidance do not clearly warn that submitted content will be retained long term. This creates a meaningful privacy and consent risk because users may provide sensitive notes or conversations under the assumption of transient processing.

Missing User Warnings

High

• Confidence: 97% confidence
• Finding: The requirements disclose use of external LLM providers via API keys, and several subsystems are described as LLM-powered, but the skill does not clearly warn users that memories may be transmitted to third-party services for processing. In a memory product handling long-term notes, conversations, and derived knowledge, undisclosed external transmission substantially increases privacy, confidentiality, and compliance risk.

VirusTotal

65/65 vendors flagged this skill as clean.