Security audit
Security checks for vulnerabilities and agentic risk
This skill is a documentation-style workflow helper with broad activation wording, but it does not contain code, credential handling, persistence, or hidden execution behavior.
Before installing, be aware that this skill may be invoked for ordinary PDF or editing requests because its triggers are broad. Prefer explicit invocation when you want Nano Pdf-style workflow help, and review outputs normally before applying any suggested workflow or code change.
The manifest description advertises broad activation conditions like 'work-productivity', 'nano', 'pdf', 'edit', and 'practical workflow' without clearly limiting what kinds of tasks are in scope. Ambiguous invocation language increases the chance that the skill is selected for unrelated requests, creating prompt-surface expansion and unreliable behavior across the agent system.
The trigger list includes extremely generic terms such as 'nano', 'pdf', 'edit', 'natural', and 'language', which are likely to appear in many unrelated prompts. This can cause accidental activation and scope hijacking, where the skill inserts its workflow into conversations the user did not intend, degrading routing reliability and potentially interfering with safer or more appropriate skills.
The trigger list is overly broad and includes generic terms such as "nano", "pdf", "edit", "natural", and "language", which are likely to appear in many unrelated user requests. This can cause accidental activation of the skill in contexts it was not designed for, leading to inappropriate guidance, confused routing, or interference with more suitable skills.
The trigger sentences and keywords are broad enough to match many ordinary requests involving PDFs, editing, or general workflow help, which can cause the skill to activate outside its intended scope. Overbroad activation increases the chance of incorrect tool routing, user confusion, and unintended execution paths, especially in agent environments where skills may be auto-selected from natural-language cues.
The invocation guidance lists keywords and sample triggers but does not define clear boundaries for when the skill should and should not be used. This ambiguity increases the risk of unintended activation from ordinary user phrasing, especially because terms like 'pdf', 'edit', 'natural language', and 'bug fix' are common across many unrelated tasks.
The trigger examples are phrased as broad natural-language requests rather than tightly scoped activation phrases, which raises the chance that the skill is invoked when a user is merely discussing PDFs, workflows, or bug fixing. In an agent ecosystem, accidental invocation can route tasks to the wrong skill, causing inappropriate actions, confusion, or unsafe handling of documents and workflow steps.
This file is a Chinese-language README variant and labels itself as the Chinese user guide, but it does not state that language selection is optional or how users can choose another locale. Under the policy rule, natural-language materials should not impose a language/locale without opt-in unless the limitation is explicitly justified.
The trigger keywords and example invocations are broad terms such as 'pdf', 'edit', 'natural', and 'instructions', which are common in ordinary user conversations and can cause the skill to activate outside its intended scope. In an agent environment, this can lead to unintended routing, context hijacking, or the skill being invoked for unrelated requests, reducing user control and potentially exposing workflows or outputs where they were not expected.
The example triggers are vague and largely restate generic demand language rather than showing precise user intents that should activate the skill. Poor examples train routing toward overbroad matches, making accidental invocation more likely, though the impact is somewhat lower than the manifest and keyword issues because examples are supporting rather than primary routing signals.
该技能内容整体以中文编写，文件名也指定为 zh-CN，但文中没有说明这是可选语言版本，也没有向用户提供语言/区域设置的选择。按照语言/区域政策，若技能实际面向广泛用户而强制特定语言且无明确 opt-in，可能构成自然语言策略违规。
The description says to use the skill when users ask for broad terms like work-productivity, nano, pdf, or edit, but it does not clearly define what requests are in-scope versus out-of-scope. Ambiguous enablement criteria increase the chance of incorrect invocation and unreliable behavior, especially in multi-skill environments where routing precision matters.
The default prompt includes broad everyday trigger terms such as "help me" and common productivity-related language, which can cause this skill to be invoked in situations far beyond the intended Nano PDF workflow scope. Because implicit invocation is enabled, this increases the chance of unintended routing, prompt interference, and accidental exposure of users to this skill's behavior when they did not explicitly request it.
