ClawHub
Back to skill

Security audit

Nurse

Security checks across malware telemetry and agentic risk

Overview

This is a text-only nursing documentation helper, but its medical outputs need clinician review and careful handling of patient information.

Install only if you want a nursing documentation drafting helper. Do not use it as a substitute for clinical judgment, diagnosis, prescribing, emergency decisions, or local policy. Minimize patient identifiers, confirm your organization permits entering patient information into the agent, and review every generated note, medication-related response, handover, or patient explanation before use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

High
Confidence
93% confidence
Finding
The trigger description is extremely broad, including 'any clinical scenario description' and common phrases that can appear in general healthcare conversation. This can cause unintended activation in sensitive clinical contexts, leading the skill to generate documentation or communication content without clear user intent, which is especially risky in healthcare because inaccurate or inappropriately scoped output could influence patient care or recordkeeping.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.