ClawHub
Back to skill

Security audit

Threejs Ai Skill

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only Three.js guidance skill with no executable code, persistence, credential access, or hidden behavior.

Installers should expect this skill to be invoked broadly for 3D web work. That may be slightly over-inclusive, but the inspected package is documentation-only and does not perform actions by itself.

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

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description says to use the skill whenever work 'touches' Three.js, react-three-fiber, or WebGL, and further says to apply it even when the user just says 'make a 3D scene/world/game.' This is broad invocation guidance without clear exclusion conditions or negative examples, which risks unintended activation for generic 3D requests that may not actually require this specific skill.

Content

No source excerpt is available for this finding.