ClawHub
Back to skill

Security audit

unisound-abnormal-items

Security checks across malware telemetry and agentic risk

Overview

The skill is purpose-aligned, but it handles sensitive health reports in a way that is not fully disclosed or implemented as promised.

Review before installing. Use this only if you are comfortable sending health-report content to the configured remote medical model endpoint, and de-identify reports yourself before running it. Treat saved outputs as sensitive medical data and avoid passing real API keys on shared systems via command-line arguments where possible.

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
91% confidence
Finding
The skill documentation advertises operational capabilities to read input files, write output files, and make network calls to an external model endpoint, but no corresponding permissions are declared. This creates a transparency and policy-enforcement gap: users or hosting platforms may not realize the skill exfiltrates sensitive health data over the network and persists results to disk, which is especially risky given the medical context and use of an appkey.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The script sends full medical report content to a remote LLM service, which likely includes sensitive health data, but it gives no explicit user-facing notice or consent step about network transmission. In a medical context, this creates a real privacy and compliance risk because users may assume local processing while protected health information is transmitted to an external endpoint.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The script requires an API credential via the --appkey command-line argument, which can expose the secret through shell history, process listings, job logs, or orchestration metadata. While this is not direct code execution, it is an avoidable secret-handling weakness that can lead to credential disclosure and unauthorized use of the LLM service.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.