Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with overly broad activation wording, but it does not contain code, credential handling, persistence, exfiltration, or destructive behavior.
Before installing, be aware that this skill may activate too easily because of broad keywords and implicit invocation. It appears safe as a planning/checklist helper, but users who want precise routing should narrow the triggers or invoke it explicitly by name.
The trigger phrases are broad, generic, and include common terms like 'self', 'improving', and 'proactive', which can cause the skill to activate in unrelated conversations. In an agent setting, overbroad activation increases the chance of unintended workflow execution, user confusion, or the skill influencing tasks outside its intended scope.
The skill description says to use the skill when a user asks for broad concepts like work-productivity, self, improving, or proactive, which are ambiguous and likely to match many unrelated requests. In an agent environment, vague activation criteria increase the chance of unintended invocation, causing inappropriate behavioral overrides, context pollution, and reduced predictability of skill routing.
The trigger list includes extremely generic terms such as "self," "improving," and "proactive," which are common in ordinary user requests and can cause the skill to activate far outside its intended scope. Over-broad activation is dangerous because it can unexpectedly steer unrelated conversations, inject workflow guidance where it was not requested, and create opportunities for prompt-scope interference or accidental tool misuse by an agentic system.
触发关键词包含“self”“improving”“proactive”等高度常见、语义宽泛的日常词汇，且还列出了 reflection、learning、organizing、bug fix 等泛化词，容易在大量无关对话中误触发该技能。误触发会让代理在不合适的上下文中套用该工作流，造成响应偏离用户真实意图、引入不必要的自动化行为，甚至覆盖更合适的技能选择。
The trigger examples include very broad natural-language phrases such as 'Help me' and 'I need a practical workflow', which are common in ordinary conversations and can cause the skill to activate unintentionally. In an agent ecosystem, overbroad invocation increases the chance that this skill intercepts unrelated requests, leading to misrouting, unexpected execution paths, or accidental application of self-improving/proactive workflow behavior where it was not intended.
The keyword list includes highly generic terms such as 'self', 'improving', and 'proactive', which are common in ordinary user requests and therefore create ambiguous invocation boundaries. This makes accidental triggering more likely and can cause the wrong skill to intercept prompts, reducing predictability and potentially exposing downstream agent workflows to unintended behavior.
The trigger sentence is overly broad and resembles normal conversation, which can cause the skill to activate in situations the user did not intend. In an agent ecosystem, ambiguous activation expands the skill's execution scope and can route unrelated requests into this workflow, increasing the chance of inappropriate actions or prompt-surface interference.
Although this is a Chinese-language README, key usage and trigger content is presented in English, including the workflow description and sample trigger phrases. This can amount to forcing a specific language for interaction without documenting user choice or opt-in.
The example trigger phrases are generic and repetitive, showing invocation based on broad narrative text rather than clear, testable conditions. This reinforces unsafe routing behavior by training users or calling systems to activate the skill on vague similarity instead of explicit need, increasing accidental activation frequency.
技能描述中的启用条件使用了“当用户提出 work-productivity, self-improving-proactive-agent, self, improving, proactive，或需要围绕该需求获得实用流程...”这类边界不清的表述，使技能适用范围从明确主题扩展到宽泛的意图猜测。这样的模糊匹配会放大路由歧义，增加代理选择错误技能的概率，影响结果准确性和可预测性。
The skill's invocation text is extremely broad and generic, covering vague concepts like work productivity, self-improving, proactive workflows, and general implementation support, while implicit invocation is enabled. This can cause the agent to auto-select the skill in situations outside its intended scope, increasing the chance of prompt-scope takeover, unintended tool routing, or the skill influencing unrelated user requests.
