ClawHub
Back to skill

Security audit

trend-jacking

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed content-strategy skill for evaluating and drafting trend-based brand posts, with no hidden execution, credentials, persistence, or destructive behavior found.

Before installing, be aware that this skill may activate for broad trend or virality requests and may route completed drafts toward a scheduling/publishing workflow. Keep human review in place for anything public-facing, especially brand posts tied to news or cultural moments.

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
96% confidence
Finding
The invocation description includes generic phrases like "trend," "trending," and "make this go viral," which can overlap with ordinary conversation and unrelated requests. Although some examples are specific, the trigger scope is still broad enough that the skill could activate in contexts where the user is not clearly asking for this exact workflow.

Static analysis

No suspicious patterns detected.