ClawHub
Back to skill

Security audit

Product Monster Feature List

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese product-planning helper that formats feature lists using a bundled CSV template, with no code execution or sensitive access.

Install this if you want Chinese-language Feature List tables for product planning. Users needing another locale or a different column schema should expect to adjust the template or request translated output.

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
  • 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
90% confidence
Finding

The 'When to Use This Skill' section says the skill applies when a user wants to break down business requirements, flowcharts, or rough ideas into a structured feature list. These triggers are fairly expansive and do not provide negative examples or clearer scope limits, which could cause the skill to be invoked for common product-planning discussions that do not actually require this specialized output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This CSV includes feature names, descriptions, and interaction phrases only in Chinese, and there is no natural-language indication that the skill or document is limited to Chinese-speaking users or a China-specific product context. Under the policy rule, forcing a specific language without user opt-in or documented justification is a locale-policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.