Back to skill

Security audit

Natural Language to SVG Vector Graphic Code

Security checks for vulnerabilities and agentic risk

Overview

This skill only teaches the agent to generate SVG graphics from prompts and does not request sensitive access or run code.

Before installing, understand that the skill will guide SVG generation using built-in shapes and sample templates. It appears safe for normal design/code assistance, though users should still review generated SVG before embedding it in production content.

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
  • 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)

Hidden Instructions

High
Category
Prompt Injection
Confidence
70% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

svg
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 400 300" width="100%" height="100%">
  <!-- content -->
</svg>