Test Curl 2

• Outcome: Pass
• Latest audit: Jun 8, 2026 at 1:30 AM UTC
• Version:
  1.0.0

Overview

This is a disclosed parenting and emotional-support skill with no packaged executable code or network behavior, though its activation language is broader than ideal for sensitive topics.

Install only if you want a Chinese-language parenting psychology support prompt. Treat it as educational support, not therapy or crisis care, and be aware that broad help-seeking phrases may activate the skill even when your request is only loosely related to parenting.

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 (2)

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: The trigger list includes very broad distress phrases such as general help-seeking language, which can cause the skill to activate in contexts far outside parenting support. In a psychologically sensitive skill, accidental activation can misroute unrelated conversations into mental-health framing, creating inappropriate guidance, privacy overreach, or incorrect crisis handling.

Vague Triggers

Medium

• Confidence: 82% confidence
• Finding: Stating that 'any user input' can enter the analysis flow defines the scope too broadly and weakens topic isolation. This increases the risk that unrelated, sensitive, or adversarial input is processed as parenting or crisis content, leading to overcollection of context, false crisis escalation, or unsafe advice in the wrong domain.

VirusTotal

64/64 vendors flagged this skill as clean.