Security audit

Medical Triage

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple medical-message triage classifier, but it lacks guardrails for a high-stakes medical workflow.

Install only if you will use it as human-reviewed decision support. Do not let it autonomously triage, route, delay, or close patient messages, and add explicit emergency-care and clinician-review safeguards before operational use.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: This is a true safety vulnerability because the skill performs medical urgency classification but nowhere warns that outputs are informational only and must not replace clinician judgment or emergency services. In a medical triage context, users or downstream systems may over-trust the model's categorization, causing delayed emergency care, unsafe automation, or misrouting of life-threatening messages.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.