persistent_user_memory

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:13 PM UTC
• Version:
  1.0.0

Overview

This skill persistently stores a local personal memory profile, which is privacy-sensitive but clearly matches its stated purpose and is disclosed.

Install only if you want OpenClaw to maintain a durable local profile about you and your contacts. Periodically review ~/.openclaw/memory/user_profile.json, avoid storing secrets or highly sensitive data, and use the documented forget/reset requests when memory is wrong or unwanted.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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 (3)

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The README explicitly states that the agent updates personal memory 'silently, without interrupting your workflow,' which means personal data can be written persistently without an explicit just-in-time notice or confirmation. Even if storage is local, silent ongoing writes of user preferences, contacts, and interaction summaries create privacy and consent risks, especially on shared machines or where users may not realize what is being retained.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill is explicitly designed to create persistent, structured memory about a user and their contacts, but the overview does not clearly warn that personal data and interaction history will be stored by default across sessions. This undermines informed consent and increases the risk that users disclose or permit retention of personal information they did not realize would be persisted.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill instructs the agent to update memory silently after learning new facts and to perform automated startup hygiene that modifies stored data without explicit user-facing notice. Silent writes and silent maintenance reduce transparency, make auditing difficult, and can lead to unauthorized retention, alteration, or deletion of personal data without meaningful user awareness.

VirusTotal

65/65 vendors flagged this skill as clean.