ClawHub
Back to skill

Security audit

Data Visualization Designer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward data visualization helper with no hidden execution, persistence, or privileged access in the inspected artifact.

This skill appears safe to install for chart and visualization work. Users should still avoid embedding sensitive or private datasets into browser-ready chart files unless they intend that data to be present in the generated output, and should review any generated HTML that loads third-party chart libraries from a CDN.

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
Confidence
88% confidence
Finding
The skill’s invocation language and workflow extend beyond visualization into general data exploration and analysis, which can cause it to activate for broad analytical requests outside its stated niche. Over-broad triggering increases the chance the agent handles requests with inappropriate authority or produces browser-executable output in contexts where a narrower skill should not be used.

Static analysis

No suspicious patterns detected.