Security audit
Security checks for vulnerabilities and agentic risk
This workflow helper has no executable payload, but its very broad auto-invocation rules could make it affect unrelated user tasks unexpectedly.
Review before installing if you rely on automatic skill selection. The main risk is not code execution, but that generic prompts about bugs, learning, improving, or organizing may activate this skill when a narrower skill would be better; disabling implicit invocation or narrowing triggers would reduce that risk.
The description says to use the skill when a user asks for broad concepts like work-productivity, self, improving, or proactive, without defining clear limits. This makes accidental invocation likely in many benign conversations, increasing the chance that the skill hijacks routing or influences responses in contexts where it was not requested.
The trigger list includes extremely generic terms like "self," "improving," and "proactive," which are common in ordinary user requests and can cause the skill to activate outside its intended scope. In an agent system, this can lead to prompt-routing errors, unexpected instruction injection into unrelated tasks, and reduced user control over which workflow is applied.
The trigger keywords include extremely broad everyday terms such as "self", "improving", and "proactive", which can cause this skill to activate for many unrelated requests. Over-broad activation increases the chance that the agent routes users into the wrong workflow, producing irrelevant actions or outputs and potentially bypassing more appropriate safety or domain-specific handling.
The trigger examples use broad, ordinary phrases such as 'help me' and 'I need a practical workflow' combined with generic terms like 'self' and 'improving', which can cause the skill to activate in contexts the user did not intend. In an agent ecosystem, overbroad invocation increases the chance of misrouting tasks, unwanted automation, or accidental use of this skill in place of a more appropriate one.
The trigger sentence is broad and conversational enough that normal user requests could accidentally invoke this skill outside its intended context. Because the skill is positioned as a proactive, self-improving workflow helper, unintended activation could cause the agent to apply the wrong workflow, produce irrelevant actions, or interfere with safer skill routing.
This trigger pattern uses a generic request form ('I need a practical workflow for ...') that is likely to overlap with many benign user prompts, increasing the chance of unintended skill invocation. In an agent ecosystem, overbroad routing can misapply instructions, create confusing outputs, and bypass more appropriate specialized skills.
The trigger phrases are broad, generic, and overlap with ordinary user requests such as asking for practical help or a workflow. This can cause the skill to activate in unintended contexts, increasing the chance that users are routed into an expansive self-improving/proactive workflow they did not explicitly request, which is especially risky for agentic behavior.
The skill description defines applicability in very broad and ambiguous terms, including generic concepts like work productivity, self, improving, and proactive, without clear boundaries. This makes accidental invocation more likely and can lead the agent to apply this skill outside its intended context, reducing reliability and potentially interfering with safer or more specialized skills.
The default prompt and description are highly generic and broad, covering many common user intents such as workflow help, analysis, implementation support, and adjacent skills. This increases the chance of unintended invocation, causing the wrong skill to activate in unrelated contexts and potentially exposing users to inappropriate automation or instruction flow.
Enabling implicit invocation without narrow trigger constraints allows the platform to auto-select this skill based on vague semantic matches rather than explicit user intent. In combination with the broad description, this can cause overreach, where the skill is invoked unexpectedly and influences tasks outside its intended domain.
This file is labeled as a Chinese README (README.zh-CN.md), but key instructional and descriptive content remains in English, including demand description, usage text, and trigger phrases. That creates an inconsistent language experience and may violate a language/locale policy if users expect the localized file to be fully Chinese without being offered a choice.
The file specifies trigger sentences only in English while the evidence section includes Chinese-language sources and suggests a broader audience. Because the skill does not indicate any user language choice or opt-in, the trigger/interface language appears implicitly fixed rather than user-selectable.
