Security audit

Mobile Responsive Layout Fixer

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only responsive layout helper with some broad activation wording but no evidence of hidden execution, data access, persistence, or destructive behavior.

Before installing, be aware that this skill may be selected for broad layout or frontend requests because implicit invocation is enabled. It appears safe as a guidance skill, but tighter trigger wording would improve user control in multi-skill environments.

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 (11)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are written as broad natural-language requests that a normal user could easily say outside an explicit opt-in flow. That increases the chance of unintended skill activation, causing the agent to route work to this skill when the user did not specifically mean to invoke it. In this context, the skill is not inherently high-risk, but overbroad invocation can still create reliability, privacy, and control issues in multi-skill environments.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger phrases are very broad and can activate the skill for generic requests about workflows, layout, or responsiveness without strong scoping. In an agent ecosystem, overbroad activation can cause the wrong skill to take over user intent, leading to prompt hijacking of task routing, irrelevant guidance, or unintended handling of requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger keywords include broad terms like "layout" and "frontend," which can match many unrelated requests and cause the skill to be invoked when it was not specifically intended. Over-broad activation can route user requests into an irrelevant workflow, increasing the chance of incorrect guidance, prompt-surface expansion, or accidental interference with more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example triggers use vague natural-language phrasing such as "Help me" and "I need a practical workflow for," which are common in ordinary conversation and may encourage ambiguous or overly eager matching. This makes unintended invocation more likely, especially in agent systems that learn from examples or use semantic similarity to select skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The usage description is vague about when the skill should activate, especially because it mixes broad topic labels with open-ended support requests like analysis or implementation help. Ambiguous activation boundaries increase the chance of over-triggering the skill on routine design or frontend questions where this specialized workflow is not intended.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger keywords are broad and overlap with common frontend discussions such as 'layout', 'frontend', and 'responsive design'. This can cause the skill to activate in unrelated contexts, leading to inappropriate routing, unintended instruction injection into ordinary conversations, and reduced trust in agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The default prompt and description use broad, everyday terms such as 'creative-and-content', 'layout', and 'analysis', which are likely to match many unrelated user requests. This can cause the skill to be invoked outside its intended scope, increasing the chance of unnecessary context injection or unintended agent behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: Enabling implicit invocation without clear trigger constraints allows the platform to auto-select this skill based on ambiguous user phrasing. In combination with the broad prompt text, this increases the risk of accidental activation, prompt-surface expansion, and interference with tasks unrelated to mobile UI issues.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The trigger sentence starts with a very broad phrase ('Help me'), which can cause the skill to activate on many unrelated user requests. Overbroad activation increases the chance of prompt/skill hijacking, accidental invocation, or routing sensitive conversations into a skill that was not intended for that context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 75% confidence
Finding: The file declares separate English and Chinese instruction sets, but does not state how the skill selects a language or whether the user can choose. That can create a locale-handling ambiguity relevant to language policy, especially if one variant is used automatically without explicit user preference.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 75% confidence
Finding: The documentation distinguishes English and Simplified Chinese variants, but this file itself is a Chinese-language README and does not indicate user language selection or opt-in. Because language/locale policy violations apply to all file types, presenting a locale-specific skill document without an explicit choice may conflict with policies requiring language preference to be user-driven.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.