ClawHub
Back to skill

Security audit

Healthcare

Security checks for vulnerabilities and agentic risk

Overview

This is a broad healthcare operations guidance skill, but its sensitive workflows are disclosed, purpose-aligned, and not backed by hidden code or persistence.

Install this only where the agent is authorized to help with clinic operations. Keep patient communications, record release, prescriptions, billing changes, and emergency escalation under appropriate human or provider review, and avoid granting broad access to patient records unless the deployment has privacy controls and audit logging.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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

Medium
Confidence
89% confidence
Finding
The manifest-style description says to use the skill for a very wide range of healthcare operations, from scheduling to billing to compliance and patient communication, without defining specific trigger phrases, scope boundaries, or exclusion conditions. In a routing system, this breadth could overlap with many ordinary clinic-related requests and increase unintended invocation risk.

Static analysis

No suspicious patterns detected.