ClawHub
Back to skill

Security audit

wcs-add-frontend-page

Security checks for vulnerabilities and agentic risk

Overview

This skill gives workflow guidance for adding a WCS frontend page and does not contain hidden execution, persistence, exfiltration, or unrelated privileged behavior.

Install this if you work on the referenced WCS frontend codebase. Before using it, confirm the backend endpoint shapes and permission policy string for the new page, because the skill provides defaults based on existing repository conventions.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
---
name: wcs-add-frontend-page
description: "Add frontend pages to WCS (Warehouse Control System) applications"
tags: [domain-specific, frontend, api-integration, cli, memory-based]

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is written entirely in Chinese and instructs the agent in Chinese-specific workflow terms, while also expecting work on both Chinese and English i18n. There is no natural-language indication that the user may choose the interaction language, which can violate a language/locale policy when a specific language is imposed by default.

Content

No source excerpt is available for this finding.