ClawHub
Back to skill

Security audit

unisound-med-knowledge-qa

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 model API, so users should avoid sending identifiable patient data.

Install only if you are comfortable sending submitted medical questions to the configured model API. Do not include identifiable patient information unless your organization has approved that endpoint and workflow; use --dry-run to inspect parsed inputs without making a network call.

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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill documentation describes capabilities to read local files/stdin, write output files, and make outbound network requests to a remote model API, but it does not declare corresponding permissions. This creates a transparency and governance gap: operators may deploy the skill without understanding that it can access local data and transmit question content, potentially including sensitive medical information, to an external endpoint.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script sends user-supplied medical questions, and potentially metadata loaded from files/stdin, to a remote third-party API by default. In a medical context, prompts may contain protected health information or other sensitive data, and the tool provides no explicit disclosure, consent step, or sanitization before transmission, creating a real privacy and compliance risk.

VirusTotal

52/52 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.