Security audit

UAE medical-billing-uae

Security checks for vulnerabilities and agentic risk

Overview

This is a plain guidance-only medical billing skill for UAE clinics, with sensitive healthcare data mentioned in a purpose-aligned way but without strong privacy reminders.

Installers should treat this as billing-process guidance, not as permission to paste full patient identifiers into chat. Use anonymized examples where possible, keep real PHI inside approved clinic systems, and consider narrowing activation terms if the skill is installed in a workspace with broad healthcare conversations.

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 (2)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The trigger list contains broad phrases such as insurance claim, co-payment, self-pay patient, and clinic revenue that can match ordinary administrative conversations outside the intended scope. This can cause unintended invocation in contexts involving sensitive healthcare billing workflows, increasing the chance that the skill receives or influences handling of regulated patient and insurance information when it was not explicitly requested.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill explicitly instructs collection and verification of patient demographics, Emirates ID, insurance card details, and documentation in EMR, but it provides no privacy, minimum-necessary, retention, or redaction guidance. In a healthcare setting, omission of data-handling safeguards increases the risk of unnecessary exposure of personal and insurance data through prompts, logs, screenshots, or downstream systems.

Static analysis

No suspicious patterns detected.