Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with broad activation wording, but no hidden code, persistence, credential handling, or destructive behavior.
This skill appears safe to install as a planning/documentation helper. Users should be aware that its broad trigger terms and implicit invocation may cause it to activate when a more specific browser, automation, or coding skill would be a better fit.
The trigger list includes very generic terms such as "browser," "automation," "cli," and "bug fix," which are common across many unrelated requests. This can cause the skill to activate outside its intended scope, leading to misrouting, overbroad handling, or unintended influence over user workflows in contexts where a more appropriate skill should respond.
The trigger sentence is a generic everyday phrase ('I need a practical workflow for ...') that can match many unrelated user requests and cause this skill to activate outside its intended scope. Over-broad activation increases prompt-routing confusion and can lead to the wrong skill handling sensitive or irrelevant tasks, reducing reliability and potentially bypassing safer, more specialized skills.
The trigger phrases are broad and include common terms like 'browser', 'automation', and generic help requests, which can cause the skill to activate in contexts the user did not intend. In an agentic environment, overbroad activation can route unrelated tasks into this workflow, increasing the chance of unintended browser automation guidance, unsafe task handling, or confusion about which skill is in control.
The trigger phrases are broad, generic, and partially malformed, which increases the chance that ordinary user requests will unintentionally activate this skill. In an automation/browser-workflow context, accidental invocation can route users into unnecessary automation guidance or browser-oriented workflows they did not explicitly request, increasing the risk of misuse or confusion.
The invocation guidance says to use the skill for broad categories like work-productivity, browser, headless, automation, or for producing general artifacts such as checklists and analyses, but it does not clearly define boundaries or exclusions. This ambiguity increases the chance of accidental invocation for common tasks, allowing the skill to inappropriately steer responses or overshadow more specialized skills.
描述中的适用范围覆盖 work-productivity、browser、automation 等大类需求，但没有清楚限定任务边界、排除条件或最低匹配标准。这会使技能被解释为适用于大量泛化请求，从而增加误调用、错误委派和不恰当自动化建议进入用户流程的风险。
触发关键词包含 browser、automation、cli、optimized、tree、bug fix 等非常宽泛或高频日常词，会让技能在大量无关场景下被误触发。误触发本身虽不是直接代码执行漏洞，但会扩大技能介入范围，导致错误路由、越权式上下文影响，甚至让后续自动化建议在不适用场景下被采用。
The default prompt is highly generic and uses broad everyday terms like work-productivity, browser, automation, checklist, analysis, and implementation support. This can cause the skill to be selected in situations beyond its intended scope, increasing the chance of unintended execution, prompt-context interference, or overbroad delegation in user workflows.
Enabling implicit invocation without strict activation constraints allows the platform to auto-select this skill based on vague semantic matches. In this skill's context, which spans browser workflows, automation, reliability, and implementation support, that broad auto-routing increases the risk of the skill being invoked unexpectedly in unrelated or sensitive tasks.
The trigger guidance is underspecified and mixes broad keywords with vague example sentences, leaving unclear when the skill should or should not activate. In an agent system, ambiguous routing rules can cause accidental invocation on unrelated requests, expanding the skill's effective permissions and making downstream behavior less predictable.
In this Chinese-language README, the exposed trigger phrases are only written in English, which effectively forces a language choice without user opt-in. The file does not explain that English-only triggers are required or offer Chinese alternatives.
该文件名为 SKILL.zh-CN.md，主体以中文书写，但标题和用户群体描述中大量直接使用英文表述，如 “Work Productivity Agent Browser Workflow Helper” 与 “AI-agent users, skill authors...”。在未说明用户可选择语言或该技能仅面向特定语言受众的情况下，存在默认语言/术语策略不清的问题。
No suspicious patterns detected.
