ClawHub
Back to skill

Security audit

Media Writing

Security checks for vulnerabilities and agentic risk

Overview

This is a simple media-writing skill with broad copywriting guidance and no code, persistence, or hidden system access.

Installers should understand this skill may be selected for a wide range of writing tasks. It is best used for media copy, titles, storytelling, and platform-oriented content; for high-stakes legal, medical, financial, or factual current-events writing, users should still require normal verification and source checking.

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

Medium
Confidence
90% confidence
Finding
The skill description is overly broad and does not define clear activation boundaries, making it likely to be invoked for generic writing tasks beyond its intended specialization. In agent systems, this can cause scope overreach, incorrect tool selection, and policy bypass by routing unrelated requests through a broadly permissive skill.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The instructions grant expansive writing capability without guardrails, refusal conditions, or negative examples, which increases the chance the skill will handle requests outside its safe or intended scope. Because the skill also instructs authoritative formatting and citation behavior, an agent may over-trust it and apply it in contexts requiring stricter specialization or safety controls.

Static analysis

No suspicious patterns detected.