Security audit

copywriting

Security checks for vulnerabilities and agentic risk

Overview

This skill is a website marketing copywriting guide with no code execution, persistence, network access, or hidden data handling.

Installers should understand that this skill may read existing product-marketing context files in a project before drafting copy. That behavior is disclosed and useful for the task, but users should avoid storing unrelated secrets in those named marketing context files.

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

Confidence: 92% confidence
Finding: The trigger guidance is broad enough to activate on generic writing requests such as 'rewrite this page' or 'help me describe my product,' which can cause the wrong skill to be selected outside its intended website-copy scope. Over-broad routing can mis-handle user intent, suppress more appropriate skills, and lead to unintended file/context access such as automatically reading product-marketing context when not necessary.

Static analysis

No suspicious patterns detected.