Security audit

ardot-mobile-app-multi-screen

Security checks for vulnerabilities and agentic risk

Overview

This skill is a low-risk design helper for Ardot mobile app mockups, with some overly broad activation wording but no code execution, data access, persistence, or hidden behavior.

Installers should expect this skill to influence responses about app screens, mobile UI prototypes, and Ardot multi-screen design. Consider narrowing the trigger terms if accidental activation is a concern, but there is no evidence of malicious behavior or sensitive access in the inspected package.

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 (2)

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger keywords are very generic terms such as "mobile", "app", "multi", and "screen", which can match many unrelated user requests and cause the skill to activate outside its intended scope. In an agent ecosystem, over-broad activation can lead to unintended routing, user confusion, and accidental disclosure of irrelevant instructions or outputs, even if the skill itself is not overtly dangerous.

Vague Triggers

Medium

Confidence: 86% confidence
Finding: The manifest description embeds a long trigger list containing broad phrases such as 'App 原型', 'UI 原型图', and '一次画多个页面', which can match ordinary user requests beyond the intended scope. This can cause unintended invocation of the skill, leading to misrouting or over-application of the skill's behavior, though it does not by itself create code execution or data exposure risk.

Static analysis

No suspicious patterns detected.