Back to skill

Security audit

Copywriting Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only marketing copywriting skill with disclosed persuasive guidance and no hidden execution, persistence, or credential handling.

Installers should treat this as a marketing-focused persuasion aid. Avoid using it for neutral, academic, legal, medical, or financial writing unless you deliberately want promotional copy, and do not paste confidential customer data into optional external tools unless your organization allows it.

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
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
95% confidence
Finding

The activation text is broad enough to match generic writing, rewriting, or review requests, which can cause the agent to invoke this skill outside a narrow marketing/copywriting context. Over-broad routing is dangerous because it can override more appropriate domain-specific skills or apply persuasion-focused guidance where neutral writing, safety review, or factual assistance was intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

Line L015 states 'Most Americans read at a Grade 7 level' as the basis for the target, which sets a language/readability norm around a specific national audience. Because the file presents this as a general rule rather than a U.S.-specific or optional guideline, it can conflict with organizational language/locale policies requiring user or market-specific choice.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.