Security audit
Security checks for vulnerabilities and agentic risk
The skill is a generic coding-workflow helper mislabeled as a USA business migration planner, with broad automatic activation but no executable payload or credential handling.
Review this carefully before installing. It should not be relied on for U.S. business migration planning unless the publisher fixes the content. If you want the coding workflow behavior, narrow or disable implicit invocation and rename the skill so it is not triggered or trusted under the wrong purpose.
The skill description is extremely broad, combining generic action terms with vague topical scope, which can cause the agent to invoke this skill for many unrelated requests. Over-broad routing increases the chance of misapplication, confusing users, and bypassing more appropriate domain-specific skills or safeguards.
The trigger list includes highly generic terms such as 'create', 'coding', and 'skill' without contextual qualifiers, making accidental invocation likely during ordinary conversations. This can route users into an irrelevant or misleading workflow and degrade safety by causing the wrong instructions to be applied to unrelated tasks.
The skill’s declared identity ('USA Business Migration Planner') does not match its actual behavior, which is a generic vibe-coding workflow helper. This kind of semantic mismatch can cause incorrect routing, user deception, and policy bypass if downstream systems or users rely on the name/description to decide whether the skill is appropriate or safe.
The skill metadata and the requirement plan describe materially different purposes: a USA business migration planner versus a vibe-coding workflow assistant. This kind of identity mismatch can cause the wrong skill to be selected or trusted under false expectations, leading users or higher-level agents to route sensitive requests into an unrelated capability.
The README and metadata describe a generic vibe-coding workflow, but the skill is branded as a USA Business Migration Planner. This mismatch can mislead users and routing systems about the skill’s actual purpose, increasing the chance of inappropriate invocation, trust confusion, or accidental use in unrelated contexts. In an agent ecosystem, deceptive or inconsistent identity is a security-relevant integrity issue even if it does not directly execute code.
The trigger phrases are broad and resemble normal conversational requests, which can cause the skill to activate unintentionally. Over-broad activation increases the risk of context hijacking, unexpected agent behavior, and the skill handling requests outside its intended scope, especially since the documented purpose is already inconsistent with the skill name.
The trigger phrases are broad enough that the skill may activate for generic terms like 'create', 'coding', or 'vibe', causing unintended invocation outside its intended scope. In an agent ecosystem, overbroad activation can route unrelated user requests into this skill, increasing the chance of incorrect actions, confusing outputs, or unsafe workflow substitution.
The description embeds Chinese text within an otherwise English skill definition, but does not state that the user can choose their preferred language or that the mixed-language scope is intentional. This can impose a language expectation without explicit user opt-in.
The applicability description is vague and mixes broad user categories with loosely related request types, without clearly defining necessary preconditions for activation. Ambiguous scope increases the chance of misrouting and unintended use, especially because the skill’s content already appears mismatched with its title.
The trigger keywords are overly broad and include generic terms like 'create', 'coding', 'skill', and 'claude', which are likely to appear in many unrelated conversations. This can cause unintended activation, leading the system to inject irrelevant workflow instructions or route users into the wrong skill context.
The default prompt uses broad, ambiguous wording such as helping with a wide class of requests and keywords, which makes invocation boundaries unclear. In practice, this can trigger the skill for unrelated conversations and create opportunities for overreach, accidental data exposure to the skill context, or misuse by downstream automation.
The skill enables implicit invocation while providing only a vague, unconstrained description of when it should be used. This can cause the agent to activate in contexts unrelated to the user's intent, increasing the chance of prompt hijacking, unintended workflow execution, or irrelevant handling of sensitive requests.
The requirement description embeds Chinese text inside otherwise English content, which can impose a language assumption on users without opt-in. The file does not state that the skill is region-specific or that users may choose their preferred language.
The activation section is ambiguous and weakly scoped, with broad keywords and trigger sentences that do not clearly define when the skill should or should not run. In an agent ecosystem, ambiguous routing logic can lead to inappropriate tool selection, unexpected behavior, and leakage of user context into an irrelevant workflow.
The trigger sentence uses broad, natural language phrasing that could match ordinary user requests beyond the intended scope. Overbroad invocation criteria increase the chance of accidental activation, causing the agent to apply this skill in irrelevant or sensitive contexts without clear user intent.
The requirement description embeds Chinese text inside an otherwise English README, which imposes mixed-language output without any stated user opt-in or language-selection guidance. This can conflict with language/locale policy expectations for user-facing skill materials.
This README is presented as a Chinese-language document but contains substantial English instructional content and English trigger phrases, without stating whether users may choose their preferred language. That can amount to an implicit language policy or inconsistent locale behavior without user opt-in.
文件名和内容表明该技能是 zh-CN 版本，整体说明均以简体中文呈现，但文档未说明这是用户可选语言，也未提供语言切换或适用区域的明确约束。按规则，若技能隐含强制特定语言而无用户选择，属于自然语言层面的策略风险。
The default prompt includes Chinese text embedded in otherwise English content, which implies a language/locale assumption without user opt-in or explanation. This can violate language policy expectations when the skill does not clearly offer a language choice or document a justified locale constraint.
No suspicious patterns detected.
