ClawHub
Back to skill

Security audit

Korean Youtube Idea Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Korean YouTube/TikTok idea-generation prompt with no code execution, data access, persistence, or hidden behavior.

Install this only if you want a Korean-market YouTube/TikTok ideation helper. Be aware that it may localize suggestions toward Korean audiences even when a request is somewhat general, and the manifest formatting may need cleanup for reliable skill loading.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description is triggered by very broad, common content-planning scenarios, which increases the chance that the agent will invoke this skill for many unrelated requests without clear user intent. Over-broad routing can cause inappropriate skill selection, unwanted steering into a specific workflow, and reduced user control over outputs.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill hard-codes a Korea-specific audience and locale focus without requiring user opt-in, which can silently override the user's actual language, geography, or audience needs. In an agent environment, this can bias recommendations, misroute requests, and produce inappropriately localized outputs that do not match the user's intent.

Content

No source excerpt is available for this finding.