ClawHub
Back to skill

Security audit

Customer Persona Copy Map

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only marketing copy skill with disclosed safety limits and no code execution, network, credential, or persistence behavior.

Before installing, use this for evidence-based messaging work and avoid targeting or excluding people based on protected traits or sensitive circumstances. Treat any demographic fields as lawful, aggregate context only, and prefer behavioral needs, purchase intent, and job-to-be-done segmentation.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s safety rules correctly warn against stereotyping on protected characteristics, but the Taobao example then operationalizes customer definition using demographic attributes like age and income. This inconsistency can normalize proxy-based audience segmentation that drifts into discriminatory profiling, especially when users extend it toward protected traits or use it as a basis for targeted messaging.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The file is a markdown skill description, so natural-language policy checks apply. Scenario 4 switches to Chinese output and a Taobao-specific context, but the skill does not state that it is multilingual or that non-English output is conditional on user preference, which can conflict with a language/locale policy requiring opt-in or clear justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.