ClawHub
Back to skill

Security audit

unisound-med-content-generation

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed medical-content helper that sends user-provided prompts to a configured medical LLM API, with no evidence of hidden persistence or unrelated behavior.

Install only if you are comfortable sending the medical prompts you provide to the configured API. Do not include identifiable patient data unless it has been de-identified and your organization permits that workflow.

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
Findings (1)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
This code sends raw user-provided medical questions to a third-party remote API, and the surrounding interface does not provide any explicit user-facing disclosure, consent flow, redaction step, or data-classification guard. In a medical-content skill, prompts may contain protected health information, case details, or sensitive clinical context, so silent transmission materially increases privacy, compliance, and data-handling risk.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.