Openclaw Self Improve

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:34 PM UTC
• Version:
  1.3.0

Overview

The skill appears to provide UX or improvement playbook guidance, with a privacy best-practice gap but no evidence of hidden execution, data exfiltration, or destructive behavior.

Before using the UX feedback or usability-testing guidance, make sure participants know what is being collected, why it is collected, where it will be stored, and how long it will be kept. Avoid sensitive personal data unless strictly necessary.

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 (1)

Missing User Warnings

Medium

• Confidence: 79% confidence
• Finding: The UX playbook recommends collecting user feedback and running usability tests on users, but it does not mention consent, notice, data minimization, or handling of any personal data that may be gathered. In a self-improvement workflow, operators may copy these examples directly into real processes, creating privacy/compliance risk and unsafe collection practices even if the document is only guidance.

VirusTotal

65/65 vendors flagged this skill as clean.