Security audit

precision-oncology

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed oncology research assistant that uses PatSnap MCP services and optional web search; its main risk is that sensitive biomedical queries may be sent to third-party services.

Before installing, understand that oncology and life-science questions may be sent to PatSnap MCP services and possibly web search. Avoid entering patient-identifying, confidential, or regulated information unless your organization has approved that data flow and API-key handling model.

SkillSpector

Vulnerability Patterns

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

Findings (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The activation criteria are broad enough to auto-load on generic biomedical or disease-treatment questions, which can cause unnecessary invocation of this skill and its attached external tooling. In this skill, that matters because loading the skill can trigger mandatory connectivity checks and route user queries into third-party life-science services, increasing the chance of unintended data exposure or incorrect domain capture.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill instructs the agent to send queries to external MCP services and potentially web search without requiring explicit user consent or a clear notice that user content may be transmitted to third parties. In a medical context, users may include sensitive health, research, or business information, so silent forwarding creates privacy, confidentiality, and compliance risk.

Static analysis

No suspicious patterns detected.