ClawHub
Back to skill

Security audit

Copywriting

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent copywriting guidance skill with no executable code, persistence, network behavior, or hidden high-impact actions.

Before installing, know that this skill may activate for a wide range of marketing or website copy requests and may read local product-marketing or brand-voice context files if they exist. That behavior is disclosed and useful for its purpose, but keep those context files limited to information you are comfortable using in generated marketing 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
  • 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
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill description and frontmatter include many generic trigger phrases such as 'write copy for,' 'improve this copy,' and 'help me describe my product,' which can cause the skill to activate for loosely related requests. Over-broad invocation increases the chance of incorrect routing, unintended file/context access, and applying persuasive-marketing behavior where another narrower skill would be safer or more appropriate.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The eval explicitly expects the skill to trigger on very casual phrasing ('i need copy for my pricing page'), which encourages broad matching behavior rather than precise routing. In an agent system, overbroad invocation can cause the copywriting skill to activate on ambiguous requests, leading to wrong-skill execution, missed safeguards from more appropriate skills, and degraded reliability.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.