ClawHub
Back to skill

Security audit

unisound-common-disease-advice

Security checks across malware telemetry and agentic risk

Overview

This medical advice skill is purpose-aligned, but it sends sensitive patient information to a remote model while promising de-identification that the code does not actually perform.

Review before installing or using this skill with real patient data. Use only de-identified case text, verify the configured --base endpoint and appkey handling, and do not rely on the documented de-identification promise unless the implementation is fixed or an external control performs redaction first.

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
91% confidence
Finding
The skill documentation describes capabilities to read patient input files, write outputs, and send medical data over the network to an external/internal model API, yet no permissions are declared. In a medical context this is dangerous because operators may not realize the skill can exfiltrate sensitive health information or write files outside expected locations, undermining consent, sandboxing, and audit controls.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill sends raw patient information to a remote LLM API, but the CLI does not provide an explicit user-facing disclosure, consent step, or data-handling warning before transmitting potentially sensitive medical data. In a medical context this is especially risky because symptoms, records, and identifiers may constitute highly sensitive personal information, and silent transmission can violate privacy expectations, policy, or regulatory requirements.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.