ClawHub
Back to skill

Security audit

Screenshot To Prompt

Security checks for vulnerabilities and agentic risk

Overview

This skill only guides an agent to analyze UI screenshots and produce implementation prompts; no malicious behavior was found.

Install only if you want screenshot contents converted into implementation prompts. Review generated prompts before sending them onward, especially when screenshots contain private UI text or internal product details.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Hidden Instructions

High
Category
Prompt Injection
Content
### UI 策略

<!-- 根据实际情况选择以下一种，删除其余两种 -->

#### 骨架模式
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High
Category
Prompt Injection
Content
### UI 策略

<!-- 根据实际情况选择以下一种,删除其余两种 -->

#### 骨架模式
Confidence
70% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list includes broad natural-language phrases such as “帮我分析这个页面” and “生成实现 prompt”, which are common requests that may appear in unrelated contexts. This can cause unintended skill invocation, leading the agent to apply screenshot-analysis behavior when the user did not actually want this skill, increasing the risk of misrouting, confusion, or accidental disclosure of screenshot-derived content into downstream coding prompts.

Static analysis

No suspicious patterns detected.