ClawHub
Back to skill

Security audit

unisound-lab-report-interpret

Security checks across malware telemetry and agentic risk

Overview

The skill does what it advertises, but it handles sensitive medical reports in a way that deserves review before use.

Review this skill before installing in any environment that processes real patient reports. Use it only if the remote LLM endpoint is approved for your medical data, avoid including names or identifiers, and do not rely on the stated de-identification promise unless the implementation is changed to actually redact the report before sending.

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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding
Without declared permissions the skill's intent is opaque and cannot be validated.

Natural-Language Policy Violations

Low
Confidence
87% confidence
Finding
The natural-language description, usage instructions, and examples are written exclusively in Chinese. Under the policy rule, forcing a specific language without user opt-in can be a locale/language policy violation when no alternative language option or justification is provided.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
This code sends the full lab report content to an HTTP endpoint via the LLM caller, which may include sensitive medical data. Although the module docstring mentions use of an internal medical model, the executable path does not provide a clear runtime warning or confirmation that patient report data will be transmitted to a remote service.

Natural-Language Policy Violations

Low
Confidence
85% confidence
Finding
The prompt instructs the model to use '国内常规标准' as the default reference range, which imposes a locale-specific standard. The file does not offer a user opt-in/choice for locale or document why only domestic standards are appropriate for all uses.

VirusTotal

60/60 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.