Back to skill

Security audit

the-4p-marketing-consultant

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language 4P marketing advice skill with broad but disclosed consulting behavior and no executable, persistent, or credential-related components.

Install this if you want marketing guidance in Chinese using a 4P framework. For ambiguous business or finance questions, confirm that you want a marketing analysis; do not treat its pricing suggestions as professional financial advice.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is entirely in Chinese and does not offer a language-choice or consent mechanism, which can lead to activation for users who cannot read or verify the instructions governing the skill's behavior. This reduces transparency and informed use, and in mixed-language environments may cause confusing or unintended outputs that the user cannot effectively assess.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The activation conditions are phrased very broadly and cover common requests like generic business advice, product analysis, pricing, and strategy help. That can cause the skill to trigger outside its narrowly intended scope, increasing the chance of unsolicited instruction injection, inappropriate routing, or the model adopting this skill when a safer general-purpose response would be more appropriate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.