Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation wording but no evidence of hidden execution, data access, persistence, or destructive behavior.
Installers should be aware that the skill may activate too broadly because of generic keywords and implicit invocation. It is otherwise a low-risk documentation skill; consider narrowing triggers or invoking it explicitly when you want this specific workflow helper.
The trigger sentence is broad and resembles ordinary user language, which can cause accidental or overly eager activation of the skill outside clearly intended contexts. In an agent ecosystem, ambiguous invocation boundaries increase the chance that the skill runs on unrelated prompts and influences workflows unexpectedly.
The trigger keywords and example invocations are very broad, including generic terms like "self", "improving", and "proactive", which are likely to match ordinary user requests unrelated to this skill. In an agent ecosystem, this can cause unintended activation, context hijacking, or the skill being selected when a more appropriate and safer skill should handle the request.
The manifest description says to use the skill when a user asks for broad concepts like work-productivity, self, improving, or proactive, which makes the activation boundary ambiguous and overly expansive. This increases the chance of accidental invocation across many benign requests, which can interfere with skill selection and make prompt-routing behavior easier to manipulate.
The trigger list includes extremely generic terms such as "self," "improving," and "proactive," which are common in ordinary conversation and likely to cause unintended activation. In an agent system, this can route unrelated user requests into this skill, creating prompt-scope confusion, degraded reliability, and opportunities for adversarial users to invoke the skill indirectly through innocuous phrasing.
The trigger keywords include very broad everyday terms such as "self", "improving", and "proactive", which are likely to appear in many unrelated user requests. This can cause the skill to activate unintentionally, leading to prompt routing errors, user confusion, and possible overshadowing of more appropriate skills; in an agentic system, over-triggering can amplify unsafe or irrelevant workflow generation.
This trigger is still ambiguous because it maps a general request for a 'practical workflow' to the skill without clear scoping or consent. That makes unintended activation more likely, especially since the skill is framed broadly around productivity, self-improvement, and proactive assistance, which are common themes in normal conversations.
Despite being a zh-CN README, core descriptive content and trigger text are written in English, which can effectively force a language preference on users without opt-in. The file does not explain that the skill is intentionally English-only or offer the user a choice of language/locale.
The description defines activation using a wide and ambiguous scope—covering broad concepts like work-productivity, self, improving, and proactive—without clear boundaries or exclusions. In practice this makes the skill eligible for many loosely related conversations, increasing accidental invocation and raising the chance that the agent applies the wrong workflow, potentially exposing users to irrelevant automation or unintended changes.
The skill metadata uses very broad, generic terms in both the description and default prompt, while also enabling implicit invocation. This can cause the platform to trigger the skill for ordinary productivity-related requests that the user did not intend to route here, increasing the chance of prompt hijacking, unintended workflow execution, or incorrect delegation.
The trigger examples use generic phrasing such as 'Help me' and 'I need a practical workflow' tied to a broad requirement description, which can cause the skill to activate for unrelated user requests. In an agent ecosystem, overbroad invocation expands the skill's execution surface and can lead to unintended handling of prompts, incorrect routing, or confusing autonomous behavior.
The activation guidance is presented only in English trigger sentences, while the evidence and references include Chinese-language sources. This may imply a fixed language experience without explicit user opt-in or a documented justification for the locale behavior.
