Security audit

Mobile Responsive Layout Fixer

Security checks for vulnerabilities and agentic risk

Overview

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

Installers should be aware that this skill may activate for broad frontend or layout wording because implicit invocation is enabled. It is best used for mobile responsiveness, navbar, and cross-device UI troubleshooting; there is no artifact evidence of code execution, credential access, persistence, or data exfiltration.

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

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 (13)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation guidance does not define clear boundaries for when the skill should and should not activate, which creates ambiguity in routing and increases the chance of accidental or adversarial triggering. An attacker or even normal conversation could embed these generic phrases to steer the agent into this skill unexpectedly, causing incorrect task handling or prompt interference. Because this is a content/workflow skill rather than a high-risk execution skill, the context makes it less dangerous than code or system-access skills, but still a real security and reliability issue.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentences are written in very broad, natural language that closely resembles ordinary user requests. In systems that auto-activate skills based on phrase matching, this can cause the skill to fire unintentionally, leading to prompt-scope confusion, unwanted workflow injection, or suppression of a more appropriate skill. In this context the skill is about frontend/UI work, so the impact is operational rather than directly code-execution-related, but the broad activation surface still increases abuse and misrouting risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad enough to activate on common frontend or content-related requests, which can cause the skill to run outside its intended scope. Over-broad activation increases the chance of prompt/skill misrouting, unintended instruction injection into unrelated tasks, and user confusion about why this skill was invoked.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords are broad enough to match many ordinary frontend requests, which can cause the skill to activate outside its intended scope. Over-broad activation is dangerous because it can route users into an irrelevant workflow, increase prompt-surface exposure, and make it easier for a skill to intercept requests that should be handled by a more appropriate or safer skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The example trigger sentences use very generic wording like 'help me' and 'I need a practical workflow', which makes activation boundaries ambiguous and reinforces over-selection. This is risky because trigger examples often shape routing behavior; vague examples can cause the skill to be invoked for broad classes of unrelated requests, reducing reliability and potentially exposing users to the wrong instructions or artifacts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The skill description defines applicability very broadly, covering multiple vague categories and artifact types without clear limits. This makes accidental invocation more likely and can cause the agent to apply this skill outside its intended domain, weakening user intent matching and potentially overriding more appropriate skills or safeguards.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger keywords include broad generic terms such as "layout" and "frontend", which can cause the skill to activate for loosely related requests. Over-broad triggering can route users into an unintended workflow, creating prompt-scope confusion and increasing the chance of inappropriate or lower-quality actions in unrelated contexts.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The default prompt uses a very broad activation phrase tied to common design and content terms, which can cause the skill to be invoked in situations beyond the user's clear intent. This creates prompt-routing risk: unrelated requests may be steered into this skill, exposing user context to an unnecessary agent and increasing the chance of inappropriate or misleading actions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: Enabling implicit invocation without scope limits or exclusions allows the platform to auto-route user requests to this skill based on loose semantic matches. In a broadly described skill like this one, that can lead to over-invocation, unnecessary sharing of user inputs with the skill, and reduced user control over whether specialized behavior is applied.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The invocation examples do not sufficiently constrain when the skill should activate and instead describe broad, natural-language requests that overlap with many normal frontend or design conversations. In an agentic environment, this can lead to accidental or excessive skill invocation, which expands attack surface and makes routing behavior easier to manipulate through prompt wording.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The trigger sentence is so generic that it can match ordinary user requests about mobile layouts, navigation, or design help without a clear requirement to explicitly invoke this skill. Overbroad activation increases the chance the agent routes unrelated conversations into this skill unexpectedly, which can cause prompt hijacking opportunities, user confusion, or unintended workflow execution.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: Despite being a zh-CN README, several key user-facing sections and trigger phrases remain in English, including the requirement description and activation examples. This creates an implicit language expectation without giving users an explicit language/locale option or justification for the mixed-language behavior.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: 该技能文件为 SKILL.zh-CN.md，内容整体以简体中文面向用户，但未见提供语言选择、回退方案或说明仅在用户选择中文时使用。根据规则，未经用户选择而固定特定语言/区域设置，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.