Back to skill

Security audit

Medical Materials Figure Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only skill that helps create biomedical figure prompts and does not request unusual access or background behavior.

Reasonable to install for biomedical schematic prompt generation. Avoid including patient-identifying or confidential clinical data in prompts, verify scientific accuracy before publication, and check the privacy and rights terms of any image-generation provider you use.

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

Static analysis

No suspicious patterns detected.