第二大脑箴言

• Outcome: Pass
• Latest audit: Jun 10, 2026 at 6:52 AM UTC
• Version:
  0.1.1

Overview

The available evidence shows a mostly coherent writing/knowledge-context skill, with only a scope note about broad activation wording.

This appears safe to install, but treat it as a personal-knowledge writing helper: only let it read notes or wiki content when you explicitly want that context used, and review outputs before sharing them.

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: 90% confidence
• Finding: The invocation description uses very broad trigger phrases such as generic requests for reflections, endings, short lines, and distillation from notes/wiki context. This can cause the skill to activate on ordinary writing requests and unnecessarily read local second-brain material, increasing the chance of unintended data exposure or over-collection beyond the user's actual intent.

VirusTotal

64/64 vendors flagged this skill as clean.