ClawHub
Back to skill

Security audit

Creating Explainers

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a normal interactive-explainer authoring helper with disclosed file, research, and HTML-generation behavior.

Install this if you want Codex to build interactive HTML explainers from supplied sources or researched topics. Be aware it may activate on broad visual-explanation requests, and it may ask to read provided files or search the web to support factual claims.

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
86% confidence
Finding
The skill can be implicitly invoked, while its description and default prompt are broad enough to match many generic requests for explanations or visualizations. This increases the chance of unintended activation in contexts where the user did not clearly request this specific capability, which can lead to over-broad tool use, unexpected content generation, or misuse of attached files/research inputs.

Static analysis

No suspicious patterns detected.