心理测评

• Outcome: Pass
• Latest audit: Jun 13, 2026 at 4:45 PM UTC
• Version:
  1.0.0

Overview

This skill is a disclosed mental-health self-assessment tool that runs local scoring scripts and creates a local HTML report, with no evidence of exfiltration or hidden behavior.

Install only if you are comfortable answering sensitive mental-health screening questions and storing the resulting report locally. Avoid using it on shared devices unless you can delete the generated report afterward, and treat any severe or self-harm result as a reason to contact a qualified professional or crisis service.

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: 88% confidence
• Finding: The trigger list contains broad everyday phrases such as '心理健康' and generic test-related wording that could activate the skill unintentionally in unrelated conversations. Because this skill handles highly sensitive mental-health assessment flows and may generate reports, accidental invocation increases privacy and safety risk.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill describes generating, previewing, and delivering a local HTML report but does not clearly warn users that the report may contain sensitive mental-health screening data. This is dangerous because users may not realize their responses and risk indicators could be stored in a local file or attachment, increasing exposure through shared devices, logs, or later access.

VirusTotal

64/64 vendors flagged this skill as clean.