Back to skill

Security audit

DeepRead Medical Records

Security checks across malware telemetry and agentic risk

Overview

The skill is a disclosed medical-document extraction integration, but using it means sending patient records to DeepRead’s external API.

Install only if you are comfortable uploading the selected medical documents to DeepRead and have confirmed the vendor’s legal and security posture for PHI, including a HIPAA BAA if needed. Keep the API key in the declared environment variable, avoid hardcoding it in scripts, test redaction with synthetic data first, and review any fields marked for human review.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.