Back to skill

Security audit

generate-cosmetic-dermatology-clinic-client-education-handout

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple drafting aid for cosmetic dermatology education handouts and does not include executable code, persistence, or hidden data access.

Before installing, treat outputs as draft marketing or educational material only, and have a qualified clinician review anything patient-facing, procedure-specific, or making medical or regulatory claims.

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
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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description is broadly phrased and lacks explicit boundaries on when the skill should be invoked or what safety checks apply. In an agentic environment, ambiguous activation can cause the skill to be selected for loosely related healthcare tasks, increasing the chance of generating patient-facing medical content without sufficient qualification, review, or regulatory guardrails.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The 'Use When' trigger scope is too vague, covering general client education work for dermatologists and growth teams without limiting the content to low-risk marketing or informational drafting. Because the domain is healthcare, this ambiguity makes accidental invocation for sensitive, patient-facing, or medically regulated content more likely, which can lead to misleading health information or noncompliant materials.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.