Health Checkup Report

• Outcome: Review
• Latest audit: Jun 17, 2026 at 1:37 AM UTC
• Version:
  2.1.0

Overview

This health-oriented skill appears non-malicious, but its medical guidance should be reviewed because it may give diagnosis-like or treatment-like advice despite saying it is informational only.

Install only if you want an informational health assistant and will treat its output as discussion prompts for a licensed clinician, not as diagnosis, treatment, or supplement instructions. Do not use it for urgent symptoms or serious abnormal lab results.

SkillSpector

By NVIDIA

Vulnerability Patterns

• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• 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)

Description-Behavior Mismatch

Medium

• Confidence: 92% confidence
• Finding: The skill states it is non-diagnostic, but multiple examples cross into diagnostic language and concrete treatment advice, such as asserting likely diseases and recommending therapies. In a health context, this can cause users to rely on the model as a medical authority, creating risk of inappropriate self-treatment, delayed care, or false reassurance despite the disclaimer.

Intent-Code Divergence

Medium

• Confidence: 90% confidence
• Finding: The safety section says the skill is informational only, but later examples present confident diagnostic interpretations that undercut that safeguard. This inconsistency is dangerous because users are more likely to trust the detailed examples over the abstract disclaimer, especially for potentially serious lab findings.

VirusTotal

64/64 vendors flagged this skill as clean.