ClawHub
Back to skill

Security audit

trend-jacking

Security checks for vulnerabilities and agentic risk

Overview

This is a marketing guidance skill for evaluating and adapting trends, with clear safety checks and no executable code or hidden persistence.

Install is reasonable if you want a brand marketing workflow for reacting to trends. Before using it with any posting or scheduling tool, make sure approval rules are clear so the agent does not publish public content without the right human review.

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger list includes very broad phrases such as "trend," "trending," and "make this go viral," which are common in normal conversation and can cause the skill to activate when the user did not intend to invoke trend-jacking behavior. In a multi-skill agent, this can misroute requests, pull in additional files or downstream skills unnecessarily, and increase the chance of inappropriate automation around timely or sensitive content.

Content

No source excerpt is available for this finding.