ClawHub
Back to skill

Security audit

Comprehensive Three.js 3D graphics reference

Security checks for vulnerabilities and agentic risk

Overview

This is a Three.js reference skill with normal code examples and no evidence of hidden persistence, credential access, or unsafe automatic behavior.

This skill is reasonable to install as a Three.js reference. Review generated app code as usual before running it, especially examples that load models, textures, or decoder files from external URLs.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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)

Session Persistence

Medium
Category
Rogue Agent
Confidence
55% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · references/controls.md (reported line 25)May include surrounding context.

md
// State
controls.saveState();
controls.reset();    // Restore saved state
controls.dispose();

// Button mapping