ClawHub
Back to skill

Security audit

Clickbait Engine

Security checks for vulnerabilities and agentic risk

Overview

This skill is only a Markdown writing guide, but it broadly activates for ordinary title/caption work and instructs the agent to create potentially misleading engagement bait.

Review this before installing if you expect general-purpose writing help: it may push ordinary titles and captions toward sensational or misleading copy. It does not appear to execute code or access data, but users should only enable it where clickbait-style promotional copy is explicitly desired and should manually verify factual claims before publishing.

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 (2)

Vague Triggers

High
Confidence
97% confidence
Finding
The trigger list is overly broad and includes generic terms like "title," "hook," and "caption," which can cause the skill to activate in many normal content-generation contexts beyond intentionally sensational marketing use. That increases the chance of unrequested manipulative copy generation and makes the skill harder to safely scope or govern in multi-skill environments.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly teaches manipulation techniques such as withholding information, forcing outrage, exploiting loss aversion, and making headlines unrelated to the actual video, while providing no warning about deception, defamation, or trust harm. In context, this increases the risk of generating misleading or reputation-damaging content under the guise of engagement optimization.

Static analysis

No suspicious patterns detected.