ClawHub
Back to skill

Security audit

ORBCAFE UI Router

Security checks for vulnerabilities and agentic risk

Overview

This skill is a documented ORBCAFE UI routing and integration guide with no hidden execution, credential access, or destructive behavior.

Install this skill if you want ORBCAFE UI integration guidance. Review the npm dependency list before running it in a project, and treat the broad routing keywords as advisory if your request is ambiguous.

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 (3)

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
This markdown file contains normative instructions written as requirements in Chinese, including '执行安装与接入基线（必须）' and '每次都先给出可执行安装方式，不允许省略', without any indication that the user may choose another language. That creates a natural-language locale policy concern because the skill appears to enforce a specific language/locale without opt-in or documented justification.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The keyword routing rules include broad, generic triggers such as 'layout', 'graph', 'detail', 'assistant', and 'chat' that commonly appear in many unrelated UI requests. In a routing skill, this can misclassify ambiguous requests and send users to the wrong downstream module, causing incorrect implementation guidance, missed required setup steps, or unintended cross-skill composition behavior.

Natural-Language Policy Violations

Low
Confidence
81% confidence
Finding
The file defines trigger keywords in both Chinese and English, but it does not explain whether users may interact in either language by choice or whether any locale assumptions apply. Because routing behavior depends on language-specific terms, the absence of an explicit language/locale policy can create inconsistent handling across users.

Static analysis

No suspicious patterns detected.