ClawHub
Back to skill

Security audit

unisound-chronic-injury

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says: it reviews user-provided medical claim text by sending it to a disclosed medical-model API, with no hidden persistence or unrelated behavior found.

Install only if you are allowed to send the case text to the configured medical-model endpoint. Remove names, IDs, imaging numbers, and other sensitive identifiers before use, and avoid --output unless saving the full question and model result is intended.

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
95% confidence
Finding
The skill documentation states that the package can read input files/stdin, optionally write output files, and send prompts to an internal medical-model API, but it does not declare corresponding permissions. This creates a transparency and governance gap: callers may unknowingly provide sensitive medical text to a networked skill with file I/O capability, increasing the risk of unintended data exposure or policy bypass in environments that rely on declared permissions for review and enforcement.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The code sends full medical question content directly to an external remote API, and the skill description indicates the input commonly contains imaging reports and other sensitive health data. There is no built-in consent prompt, warning, minimization, or redaction step before transmission, so protected medical information may be disclosed to a third party without adequate user awareness or policy enforcement.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.