ClawHub
Back to skill

Security audit

Cb Customer Journey Mapper

Security checks for vulnerabilities and agentic risk

Overview

This is a descriptive marketing and customer-journey planning skill with no code execution, external access, persistence, or hidden high-impact behavior.

Installers should treat this as a planning aid, not market research proof. Validate any cultural assumptions, benchmark numbers, or conversion recommendations with customer data before making business decisions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The 'Getting Started' section uses a very generic invocation pattern ('Map the customer journey for [product] in [market]...') that can easily match ordinary user requests outside an explicit skill-selection flow. This can cause unintended activation or routing to this skill when a user is asking for general advice, leading to overbroad prompt capture and reduced user control over tool/skill selection.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The example output prescribes Chinese-language content and locale-specific assumptions without explicit user opt-in, which can cause the system to respond in an unintended language or overfit to a locale the user did not request. While not directly enabling code execution or data exfiltration, it can degrade reliability and steer outputs based on embedded examples rather than actual user preferences.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The README lists general phrases like "overseas customer journey" and "global customer experience" as trigger keywords, which can overlap with ordinary business discussion rather than a clearly scoped invocation pattern. It does not specify constraints, exact invocation behavior, or negative examples to clarify when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest sets the skill language to "en", which is a natural-language locale constraint. The file does not indicate that users can opt into another language or that English-only behavior is required for a documented regional or compliance reason.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.