Security audit

Nurse

Security checks for vulnerabilities and agentic risk

Overview

This is a single nursing-support Markdown skill with no executable code, persistence, credential use, or data access, though its healthcare trigger wording is broad and should be used carefully.

Install only if you want a skill that may respond to broad clinical scenarios with nursing-oriented documentation and communication frameworks. Treat outputs as drafting support, not clinical authority, and verify medication, consent, escalation, and scope-of-practice matters through local policy and qualified clinicians.

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

High

Confidence: 98% confidence
Finding: The trigger description is genuinely overbroad: it activates on very generic phrases and on essentially any 'clinical scenario description,' which can cause the nurse skill to be invoked in situations where the user did not intend specialized clinical handling. In a healthcare context, unintended invocation is more dangerous than usual because it can steer conversations into medical documentation or communication workflows, increasing the risk of inappropriate reliance, privacy exposure, or clinically framed outputs in ambiguous situations.

Static analysis

No suspicious patterns detected.