ClawHub
Back to skill

Security audit

ai-prompt-generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Chinese-language prompt-generator stub that prints parsed options and status messages without hidden network, file, credential, persistence, or privilege behavior.

Review that the skill is Chinese-language and appears to be a minimal/stub implementation despite paid-use language and advertised features. From the inspected files, it does not access private data, call external model providers, install dependencies, or persist changes.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (5)

External Model or Provider Selection

High
Category
Excessive Agency
Content
/ai-prompt-generator --action optimize --input prompt.txt

# 为特定模型生成
/ai-prompt-generator --task "写代码" --model claude --style detailed
```

---
Confidence
90% confidence
Finding
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

External Model or Provider Selection

High
Category
Excessive Agency
Content
## Usage
```bash
# 生成提示词
/ai-prompt-generator --task "写博客" --model "gpt-4" --style "detailed"

# 使用模板
/ai-prompt-generator --template "cot" --topic "数据分析"
Confidence
90% confidence
Finding
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
This markdown file is written entirely in Chinese, including the core skill description and examples, and does not mention any option for other languages or a justified region-specific limitation. Under the policy criteria, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The file’s descriptive and instructional content is presented in Chinese, and there is no indication that users may choose another language or that the locale is intentionally limited to a Chinese-speaking context. The policy for this category requires flagging language or locale constraints when they are imposed without user opt-in or clear justification.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
This code presents all user-facing strings in Chinese, including startup status and usage instructions, with no opt-in or alternative locale handling. That can violate a language/locale policy when users are not given a choice and the tool is not clearly documented as region-specific.

Static analysis

No suspicious patterns detected.