ClawHub
Back to skill

Security audit

Copywriter

Security checks for vulnerabilities and agentic risk

Overview

This is a copywriting guidance skill with disclosed project-context reading and no code, persistence, credential use, or external execution.

Install this if you want copywriting help that may use project documentation for audience, positioning, and brand voice. Avoid using it in projects where local customer research or internal messaging files should not be considered for generated copy.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list and description are broad enough to match many ordinary writing requests, which can cause the skill to activate in contexts the user did not explicitly intend. In an agent system, over-broad invocation expands the skill's influence over prompts and workflow, increasing the chance of inappropriate file reads, unintended instruction injection into unrelated tasks, or suppression of better-scoped skills.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill documentation repeatedly says to avoid sentence starters like "Here's" and lists them as AI-isms to eliminate. But the example under the "Good" output format begins with "Here's a draft for your GVP," which directly conflicts with those stated instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.