ClawHub
Back to skill

Security audit

Copy Editing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a copy-editing guide for improving existing marketing copy, with no executable code or hidden high-impact behavior found.

Before installing, be aware that the skill may ask the agent to read local brand or product-marketing context files if they exist, so only use it in workspaces where those files are appropriate context for copy editing.

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
Category
Not specified by scanner
Confidence
95% confidence
Finding

The evaluation expects the skill to trigger on vague, casual phrasing ('it feels too long and wordy') without tightly constraining that activation to clear copy-editing intent. Broad trigger criteria can cause the agent to invoke this skill in unrelated contexts, leading to incorrect routing, policy bypass through unintended tool/skill selection, or degraded reliability of downstream behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.