Software Data Admapix Raw Developer Helper

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 5:18 AM UTC
• Version: 0.20260911.40430

Overview

This is a documentation-only helper skill with broad auto-activation wording, but no hidden execution, credential handling, persistence, or destructive behavior was found.

Before installing, consider narrowing or disabling implicit invocation if you only want this skill for explicit AdMapix-related workflow help. The main risk is accidental activation on generic software or data requests, not hidden code execution.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (12)

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The trigger phrases are generic enough to match ordinary software-help requests, which can cause the skill to activate outside its intended scope. In an agent ecosystem, overly broad routing increases the chance that users are steered into this skill unintentionally, potentially causing incorrect handling, confusion, or unsafe delegation if the skill later performs privileged or specialized actions.

Vague Triggers

High

• Confidence: 97% confidence
• Finding: The skill description and activation guidance are broad enough to match many unrelated software or data requests, increasing the chance of accidental invocation. In an agent setting, misrouting to the wrong skill can produce irrelevant guidance, bypass more appropriate specialized safeguards, or cause unsafe assumptions in downstream workflow generation.

Vague Triggers

High

• Confidence: 99% confidence
• Finding: The keyword list includes highly ambiguous terms like 'raw', 'data', 'layer', 'apps', and 'bug fix', which are common across many benign requests and therefore likely to over-trigger. In agent ecosystems, such generic triggers can hijack routing for unrelated tasks, leading to inappropriate execution context and reducing the reliability and safety of tool or skill selection.

Vague Triggers

High

• Confidence: 98% confidence
• Finding: The trigger phrases are so broad and generic that ordinary user requests like 'help me' or 'I need a practical workflow' combined with loosely related terms could activate the skill unintentionally. This creates a routing and prompt-injection surface where the skill may engage outside its intended scope, causing irrelevant execution, data exposure through unnecessary context handling, or interference with safer/more appropriate skills.

Vague Triggers

Medium

• Confidence: 96% confidence
• Finding: The trigger phrases are broad and generic enough to match ordinary user requests unrelated to this specific skill, which can cause unintended invocation. In an agent ecosystem, overbroad routing increases the chance of the skill handling tasks outside its intended scope, leading to incorrect actions, data exposure to the wrong workflow, or reduced user control over which skill is used.

Natural-Language Policy Violations

Medium

• Confidence: 88% confidence
• Finding: The file identifies this document as the Chinese-language user guide ("README.zh-CN.md" / "中文版用户说明"), while substantial instructional content in the same file is still presented in English and there is no explicit user opt-in or language-selection guidance. This creates a mixed and effectively imposed locale experience rather than clearly offering a user language choice.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The example triggers are vague and effectively restate the broad requirement text rather than showing precise activation boundaries. That makes it harder for maintainers and routing systems to distinguish legitimate use from unrelated requests, which can amplify accidental invocation and poor task-skill alignment.

Natural-Language Policy Violations

Medium

• Confidence: 81% confidence
• Finding: 该技能文件为中文版本内容，但未向用户提供语言选择或明确声明适用对象，可能在非中文用户环境中被调用并输出错误语言的指导。虽然这更偏向可靠性/可用性问题而非直接安全漏洞，但在安全、配置或修复步骤场景下，语言错配可能造成误解和错误执行。

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: 触发关键词包含 `raw`、`data`、`layer`、`apps` 等高频通用词，容易在与该技能无关的普通软件/数据场景中误触发。误触发会把用户路由到不相关的技能流程，导致越权式上下文介入、错误建议增加，且在安全敏感场景中可能掩盖更合适的专用技能。

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: 示例触发句使用了非常宽泛的模板化表达，如 `Help me...`、`I need a practical workflow...`，而核心限定词较弱，实际会鼓励在边界不清的请求上激活技能。这样的激活歧义会放大误用概率，尤其当系统依赖示例做意图匹配时，可能把泛化的软件帮助请求错误映射到该技能。

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The skill enables implicit invocation, but its description and default prompt are broad and loosely scoped rather than tightly constrained to a narrow, well-defined trigger condition. This increases the chance the agent will auto-select the skill in unrelated contexts, causing unintended handling of user requests and potentially exposing users to unsafe or inappropriate actions from a skill that was not explicitly requested.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The activation guidance is ambiguous because it mixes broad keywords, partial sentences, and general workflow language without precise boundaries on when the skill should or should not run. In an agent environment, this can cause misrouting, over-invocation, or unintended handling of user tasks that only weakly resemble the intended requirement, reducing reliability and potentially exposing user context to the wrong skill path.

Static analysis

No suspicious patterns detected.