Security audit
Security checks for vulnerabilities and agentic risk
This skill is a documentation-only workflow helper with overly broad activation wording, but it does not install code, request credentials, persist data, or perform hidden actions.
Before installing, consider whether you want this skill to activate implicitly; its broad keywords may make it appear for unrelated web/search/API tasks. It is otherwise a low-risk documentation skill with no observed executable code or privileged behavior.
The trigger phrases are broad, natural-language prompts that can match ordinary user requests unrelated to this skill, causing the skill to activate unintentionally. In an agent environment, overbroad activation can misroute tasks, inject irrelevant workflow behavior, or increase the chance that external web/search capabilities are used when the user did not explicitly intend that path.
The skill description uses very broad activation terms like 'work-productivity', 'web', 'search', and 'analysis', which can cause the skill to be invoked for many unrelated user requests. Over-broad routing increases the chance that this skill intercepts prompts outside its intended scope, leading to inappropriate automation, misleading outputs, or unintended exposure of workflow behaviors in contexts where they were not requested.
The trigger keyword list includes highly generic terms such as 'web', 'search', 'api', 'user', and 'bug fix', which are common across many benign prompts. This can produce frequent false activations and prompt routing confusion, causing the skill to run in contexts unrelated to Tavily-style workflow assistance.
The trigger sentences and keyword list are broad enough to match ordinary user requests about work, web search, APIs, or bug fixes, which can cause the skill to activate outside its intended scope. Overbroad activation is dangerous because it increases unintended routing, may override more appropriate skills, and can expose users to irrelevant or lower-quality behavior at scale.
The trigger sentences are broad, repetitive, and include generic terms tied to common user requests, which increases the chance the skill will activate outside its intended scope. In an agent ecosystem, unintended invocation can route unrelated tasks through this workflow, causing incorrect actions, noisy tool usage, or unsafe handling of web/search tasks that the user did not explicitly request.
This Chinese README contains substantial English content and English trigger phrases, but it does not state whether the skill supports multiple languages by user choice or requires a specific locale. That can amount to an implicit language-policy constraint without opt-in or justification.
The example trigger phrases are vague and largely restate the marketing description rather than defining clear invocation boundaries. Ambiguous examples train calling systems or users to activate the skill imprecisely, which compounds routing errors and reduces predictability of when the skill should be used.
技能描述使用了非常宽泛的自然语言范围，如“work-productivity, tavily, web, search, via”以及“需要实用流程、产物、检查清单、分析或实现支持时使用”，几乎覆盖大量常见办公与搜索相关请求。这种模糊边界会扩大技能匹配面，使路由系统更难判断何时真正应调用该技能，增加错误激活和响应污染风险。
触发关键词列表包含大量高频、通用词，如“web”“search”“api”“user”“alternative”“bug fix”，且没有要求组合条件或明确上下文约束。这会导致技能在与其目标任务无关的普通对话中被误触发，进而让代理偏离用户真实意图，插入不相关流程或操作建议。
The default_prompt is overly broad and vague, with repetitive marketing-style language rather than a narrowly scoped invocation trigger. This can cause the skill to activate on loosely related user requests, increasing the chance of unintended tool use, irrelevant assistance, or prompt-routing mistakes that may expose users to unsafe workflow guidance.
Enabling allow_implicit_invocation without strict trigger constraints means the platform may invoke this skill automatically based on weak semantic matches. In a skill covering broad topics like productivity, web, and search workflows, that raises the risk of accidental activation, user confusion, and execution in contexts the user did not clearly authorize.
Line L05 includes Chinese text ('搜索-style') inside an otherwise English README, while the file does not explain language selection or indicate user opt-in for mixed-language behavior. This can conflict with language/locale consistency expectations unless the skill explicitly offers or documents language choice.
The description includes the Chinese term "搜索-style" inside otherwise English instructions, which introduces a language/locale assumption without explaining whether the skill is bilingual or allowing user language preference. This can conflict with language policy expectations when a skill appears to impose or default to a specific locale implicitly.
示例触发句以通用开场语如“Help me”“I need a practical workflow”开头，并紧跟较泛化的需求描述，容易与大量正常用户表达重叠。虽然示例本身不执行代码，但它会训练或暗示路由器在缺乏精确约束时触发该技能，从而增加误调用概率。
The natural-language description and default prompt include Chinese text ("搜索-style") embedded in otherwise English content, but the file does not indicate that language selection is user-configurable or optional. This can impose a language or locale assumption on users without explicit opt-in.
