ClawHub
Back to skill

Security audit

unisound-med-medication-rehab

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed medical Q&A wrapper that sends user-provided questions to a configured medical LLM endpoint, with no evidence of hidden persistence, broad local access, or unrelated behavior.

Before installing, users should understand that medical questions may be transmitted to the configured API service and should remove patient identifiers or regulated health information unless their organization has approved that endpoint, key handling, and retention policy.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill declares no permissions, yet its documented behavior clearly involves reading local input files, optionally writing output files, and sending prompts to a remote medical-model API. This mismatch can mislead integrators and users about the skill's actual capabilities, reducing informed consent and making unsafe deployment more likely.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documentation names an external API endpoint and states that user questions are sent to an internal medical LLM, but it does not give a clear, prominent warning that submitted medical questions may be transmitted off-host to a remote service. In a healthcare context, users may include sensitive patient data, so lack of explicit disclosure materially increases privacy and compliance risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill sends user medical questions and associated metadata to a remote third-party API, but it provides no explicit notice, consent flow, minimization, or redaction of potentially sensitive health information. In a medical-use context, prompts may contain diagnoses, medications, rehabilitation details, or identifiers, so undisclosed transmission materially increases privacy, compliance, and data-governance risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.