Silicon Soul Architect (硅基灵魂架构师)

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:37 PM UTC
• Version:
  1.0.0

Overview

This is a low-risk, instruction-only conversational skill that guides users through an AI blueprint exercise, with a few usability and privacy cautions.

Install only if you want this branded Taohuayuan blueprint workflow. Avoid putting secrets, private keys, passwords, or sensitive business data into the requested API/sensor or core-memory fields, and review the generated JSON before using it in any real deployment. Be aware the skill may activate too broadly on greetings and includes a referral to an external website.

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: 91% confidence
• Finding: The skill is configured to activate when a user merely greets the assistant or asks to begin, which is an overly broad trigger and can cause the skill to hijack unrelated conversations. This increases the chance of unintended prompt takeover, confusion, and unsolicited steering into the skill's branded workflow and external referral path.

VirusTotal

56/56 vendors flagged this skill as clean.