Back to skill

Security audit

Marketing Copywriting

Security checks for vulnerabilities and agentic risk

Overview

This is a non-executable marketing-writing prompt with some overly broad business-language and data-sharing guidance gaps, but no hidden code, persistence, or automatic access.

Before installing, treat this as a broad business-writing prompt rather than a tightly scoped marketing-copywriting assistant. Do not paste secrets, credentials, customer personal data, regulated records, or confidential documents unless you have approval and have redacted unnecessary details.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The top-level description is broad enough that the skill's activation boundary is unclear, which can lead to unintended triggering in unrelated business contexts. When a skill appears applicable to many domains, it can collect unnecessary data and produce outputs outside its intended safety and competency limits.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill is labeled as marketing copywriting, but the body describes broad business operations, strategic decision support, and process optimization capabilities. This mismatch can cause overbroad activation and user trust confusion, increasing the chance the skill is invoked in contexts far beyond its stated purpose and receives sensitive business information it should not handle.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The use cases list generic enterprise and business scenarios rather than concrete marketing-copywriting triggers. This makes the skill look suitable for broad operational or strategic workflows, increasing the risk of inappropriate invocation and misuse with sensitive or irrelevant data.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly asks users to paste business context, data, and documents but provides no warning to avoid confidential, regulated, or personal information. In practice, this can lead users to disclose proprietary data, customer records, contracts, or regulated material to a skill that does not set minimization or handling expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.