ClawHub
Back to skill

Security audit

Immersive Presentations

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent guide for creating interactive web presentations and does not show hidden data access, persistence, or unsafe authority.

Install this if you want the agent to create interactive web presentation plans or implementations. Review generated web code and any added assets/packages as you normally would for a frontend project, especially when the agent chooses to use GSAP, canvas, WebGL, or external media.

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 default prompt is very broad and can be triggered by many ordinary requests about creating presentations, increasing the chance this skill is invoked when a user did not explicitly want a web-based interactive artifact. That can cause scope confusion, unintended tool activation, and potentially expose downstream generation or rendering surfaces more often than necessary.

Static analysis

No suspicious patterns detected.