Medical Entity Extractor

• Outcome: Pass
• Latest audit: May 28, 2026 at 10:24 AM UTC
• Version:
  1.0.0

Overview

This instruction-only skill appears focused on extracting medical details, but users should treat patient text as sensitive because Claude API processing may send it outside the local environment.

Before installing, confirm that your organization permits patient messages to be processed by the configured LLM provider, de-identify text where practical, and use the extracted entities as assistive output that still requires clinical review.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill processes patient messages containing health information and explicitly notes that data may be sent to the Claude API, but the privacy section frames processing as local and does not clearly disclose the implications of transmitting PHI/PII to an external LLM provider. In a medical context, incomplete disclosure can cause operators to unknowingly send sensitive regulated data to third parties, creating compliance, confidentiality, and data governance risk.

VirusTotal

66/66 vendors flagged this skill as clean.