Back to skill

Security audit

Huo15 Openclaw Design Director

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed design-direction advisor with no executable code, persistence, credential handling, or hidden data flows.

Install if you want a Chinese-language design-direction advisor that can prepare structured briefs for a related frontend-design workflow. Be aware that generic phrases like design direction or 设计方向 may route ordinary design discussions to this skill.

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
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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The alias list includes highly generic terms such as “设计方向”, “方向选型”, and “design direction”, which are likely to collide with ordinary user conversation. In an agent routing system, this can cause unintended invocation of the skill, leading to prompt-scope confusion, misrouting, and unexpected cross-skill context handoff.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger scenario allows activation on vague requests like 'help me choose a direction' and even permits automatic triggering when another skill decides to defer. This weak boundary definition increases the chance of accidental invocation and unauthorized workflow chaining, especially because the skill is designed to pass structured context into another skill.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger-word section repeats broad natural-language phrases without scope limitation or disambiguation rules. This makes the skill easier to trigger accidentally during normal multilingual design discussions, increasing the risk of inappropriate routing and unintended use of downstream resources or linked skills.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

L003-L004 使用中文作为显示名称和主体描述,同时文档绝大部分说明也默认中文,没有声明可根据用户语言偏好切换。按规则,这种默认强制单一语言而未提供 opt-in/choice 可能构成语言/locale 策略问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.