ClawHub
Back to skill

Security audit

3dgs Visualizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent visualization helper that creates local charts and does not show hidden credential access, remote execution, persistence, or destructive behavior.

Before installing, expect the skill to generate local Python scripts and visualization files in your workspace. Use non-sensitive data or review generated HTML/PDF/PNG outputs if the charts contain private research results, and choose output paths deliberately.

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
  • 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)

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file describes the skill's behavior, and the workflow explicitly says it will write a Python script to .temp/. Because markdown files should warn about behaviors that affect user data or system state, this is a minor missing disclosure about file creation.

Content

No source excerpt is available for this finding.