Learn me

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:17 PM UTC
• Version:
  0.5.2

Overview

This skill is coherent but privacy-sensitive: it asks optional personal questions and keeps local notes only after user-confirmed setup.

Install this only if you want OpenClaw to occasionally ask personal follow-up questions and keep local notes about topics to revisit or avoid. Confirm any cron schedule before enabling it, review or delete memory/next-questions.md if desired, and avoid sharing secrets or topics you do not want remembered.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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

Findings (1)

Vague Triggers

Medium

• Confidence: 83% confidence
• Finding: The skill is explicitly designed to proactively learn personal information through ongoing conversation and scheduled prompts, but its activation scope is described very broadly. That broad framing can justify frequent, ambiguous, or socially engineered questioning, increasing the chance of over-collection of user data or unexpected prompting beyond what a user reasonably expects from a manually invoked skill.

VirusTotal

64/64 vendors flagged this skill as clean.