Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with broad activation wording, but I found no hidden code execution, credential access, persistence, or destructive behavior.
This skill is reasonable to install if you want a general proactive-agent workflow helper. Be aware that its trigger words are broad and implicit invocation is enabled, so it may be selected for ordinary task or bug-fix requests unless your agent lets you disable or narrow automatic skill routing.
The trigger phrases are very broad and include common terms like 'help me', 'practical workflow', 'task', and 'needs', which can cause the skill to activate for many unrelated everyday requests. In an agent ecosystem, this increases the chance of unintended routing, priority hijacking, or inappropriate application of this workflow in contexts the user did not intend.
The trigger phrases are broad, generic, and overlap with ordinary user requests such as asking for practical workflows or help with tasks. This can cause the skill to activate unintentionally in unrelated contexts, leading to misrouting, unexpected agent behavior, and possible expansion of the skill’s effective authority beyond what the user intended.
The manifest description says to use the skill when a user asks for broad concepts like work-productivity, proactive, transform, task, or practical workflow support, which are common across many benign requests. This ambiguous invocation language can cause excessive matching and unintended selection of the skill, increasing the likelihood of misrouting, overreach, or interference with more appropriate skills.
The trigger list includes highly generic terms such as "proactive," "transform," "task," "needs," and "bug fix," which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance this skill is invoked accidentally and steers users into irrelevant or unintended workflows, creating prompt-routing and control-scope risk rather than direct code-execution risk.
The skill description says it should be used when users ask for broad categories like work-productivity, proactive, transform, or task, without clear scope limits. This unclear and expansive enablement condition increases the chance of accidental invocation across many benign requests, which can misroute user intent and create unreliable or policy-bypassing workflow composition.
The trigger list includes very broad everyday terms such as "task", "needs", and "bug fix", which can cause the skill to activate in many unrelated conversations. Over-broad activation is dangerous because it can hijack routing, inject irrelevant workflow behavior, and crowd out more appropriate or safer skills in contexts the user did not intend.
The skill enables implicit invocation, but its description and default prompt are broad and generic rather than narrowly scoped to specific user intents. This can cause the agent to invoke the skill in situations the user did not clearly request, increasing the risk of overreach, unintended actions, or prompt-surface abuse from a skill that is meant to operate proactively.
This Chinese-language README presents key usage and trigger content in English, including the main behavior description and invocation phrases, without indicating that the user can choose their preferred language. That can amount to a language-policy issue because the skill appears to impose English phrasing in a locale-specific document without opt-in or justification.
The trigger phrases are extremely broad and map to ordinary user requests like asking for practical workflows or help with tasks, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of unintended delegation, prompt hijacking of benign requests into this skill, and user confusion about why this skill was selected.
The README states that files are split into English and Chinese variants, but this file does not explain how the user's preferred language is selected. That can create an implicit locale constraint unless the skill explicitly asks or allows the user to choose their language.
The document includes Chinese-language evidence titles and URLs alongside English instructions and trigger text, but it does not explain whether the skill is intended to operate in multiple languages or how language choice is determined. This can create an implicit locale assumption without explicit user opt-in or documented justification.
