Security audit
Security checks for vulnerabilities and agentic risk
This skill is a low-impact workflow helper with overly broad activation wording but no code, persistence, credential handling, or hidden behavior.
Before installing, be aware that this skill may activate too easily on generic weather, API, key, or productivity requests. It appears safe in terms of local system impact, but users may prefer narrower triggers to avoid irrelevant workflow guidance.
The trigger sentence is so broad and awkwardly truncated that it can match ordinary user requests unrelated to this specific skill, causing unintended invocation. In an agent ecosystem, overbroad routing increases the chance that this skill intercepts prompts outside its intended scope and influences workflows the user did not mean to delegate here.
The trigger phrases are broad enough to match ordinary requests about productivity, weather, APIs, or bug fixing, which can cause the skill to activate outside its intended scope. In an agent ecosystem, this creates routing ambiguity and increases the chance that unrelated user tasks are intercepted or influenced by this skill, degrading safety and reliability.
The skill description is extremely broad and includes generic domains like 'work-productivity', 'api', and requests for any 'workflow, artifact, checklist, analysis, or implementation support'. This can cause the skill to be invoked for loosely related prompts, increasing the chance of inappropriate routing, prompt-surface expansion, and unintended application of weather-specific guidance to unrelated tasks.
The trigger keyword list contains vague, high-frequency terms such as 'api', 'key', 'required', 'users', and 'bug fix' without contextual constraints. In an agent ecosystem, such generic triggers can lead to frequent accidental invocation, causing the wrong skill to intercept requests and potentially exposing users to irrelevant or unsafe actions under an incorrect workflow.
触发关键词包含非常通用的词，如“weather”“current”“api”“key”“required”“users”等，会让技能在与其真实用途无关的大量上下文中被匹配和激活。这会造成错误路由、意外介入其他任务，并可能把本技能中的流程或建议注入到不相关对话中，扩大提示面和误用面。
The trigger sentence is extremely broad and generic, making accidental or context-inappropriate activation likely. In an agent ecosystem, overbroad routing can cause the wrong skill to handle unrelated prompts, leading to confusing behavior, unsafe delegation, or leakage of user context into an unintended workflow.
The invocation description uses a very common request pattern ('I need a practical workflow for...') without sufficient specificity, which can cause accidental activation during normal conversation. This is especially risky because the skill mixes broad work-productivity terms with weather/API terms, making routing ambiguous and potentially hijacking unrelated tasks.
The file is a Chinese-language README, but key user-facing descriptive content is presented in English without any opt-in or language selection. This can amount to a language-policy issue because the documentation implicitly forces a specific language experience instead of explicitly offering the user a choice.
The example trigger sentences use broad natural language patterns like 'Help me' and 'I need a practical workflow', which are common across many unrelated user requests. These examples reinforce overbroad matching behavior and make the skill more likely to activate outside its intended context, reducing routing integrity and increasing the attack surface for misclassification or prompt interference.
技能描述将适用范围扩展到“work-productivity, weather, current, forecasts, api”以及几乎任何“workflow、artifact、checklist、analysis、implementation support”请求，边界非常模糊。这种宽泛声明会让编排器在大量普通生产力或 API 场景中错误选择该技能，导致权限/上下文错配和不可靠输出。
示例触发句使用“Help me”“I need a practical workflow”这类通用求助模板，且后接内容被截断，进一步训练或暗示系统对泛化求助语句进行匹配。这会放大误触发问题，使该技能在大量普通支持请求中被调用。
The default prompt embeds a very broad invocation phrase tied to common concepts like work productivity, weather, current, forecasts, and API help, which increases the chance of accidental or implicit triggering in unrelated user conversations. Because implicit invocation is enabled, this broad matching can cause the skill to activate unexpectedly, exposing users to unintended prompt injection surface, workflow interference, or unreviewed skill behavior.
This trigger is ambiguously phrased as a general request for 'a practical workflow,' which lacks boundaries and can match many unrelated user requests. Because the skill is framed as broadly useful for artifacts, checklists, analysis, or implementation support, the ambiguous trigger increases the chance of unintended invocation and misrouting.
