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 code, credential access, persistence, exfiltration, or destructive behavior.
Install only if you want a broad workflow-planning helper that may be invoked automatically for general productivity-style requests. Prefer explicit invocation or tighter trigger wording if you want to avoid it influencing unrelated tasks.
The manifest description says to use the skill whenever a user asks for broad categories like work-productivity, proactive, transform, task, or practical workflow support, which are common across many benign requests. This ambiguity can lead to over-invocation, causing the skill to be selected outside its intended scope and potentially exposing users to irrelevant or conflicting instructions.
The trigger list includes very generic terms such as "proactive," "task," "needs," and "bug fix," which can cause the skill to activate for many unrelated user requests. Overbroad activation increases the chance of inappropriate routing, unexpected instruction injection into unrelated contexts, and accidental override of more appropriate skills.
The skill description defines applicability in very expansive terms, covering broad categories like work-productivity, proactive, transform, and task, plus any request for practical workflows, artifacts, checklists, analysis, or implementation support. This weak scoping makes accidental invocation likely and can cause the skill to be selected for general-purpose tasks it was not specifically designed to handle.
The trigger keywords include very broad everyday terms such as “task”, “needs”, and “partners”, which can cause the skill to activate in many unrelated conversations. Over-broad activation increases the chance that this skill intercepts requests outside its intended scope, leading to misrouting, confusing behavior, or unintended disclosure of context to an unnecessary workflow.
The trigger sentence begins with a very broad everyday help request pattern, which can cause the skill to activate in situations far outside its intended scope. In an agent ecosystem, overly generic activation cues increase the chance of accidental routing, prompt hijacking of unrelated tasks, and inappropriate invocation of workflow logic on user inputs that were not meant for this skill.
The trigger phrases are extremely broad and include generic terms like "help me," "practical workflow," and common productivity concepts, which can cause the skill to activate for many unrelated requests. In an agentic workflow context, unintended invocation can route user tasks through the wrong behavior set, leading to confusing actions, incorrect outputs, or inappropriate automation.
The trigger phrases are broad and map to common words like 'task', 'transform', 'proactive', and generic help requests, which can cause the skill to activate in unrelated conversations. In an agent ecosystem, overbroad invocation can silently route user requests into this workflow, creating prompt-scope confusion, unintended execution paths, or interference with a more appropriate skill.
文件名 SKILL.zh-CN.md 与正文内容均表明该技能以简体中文（中国区）呈现，但文中未说明这是可选本地化版本，也未向用户提供语言选择或切换方式。对于通用工作流辅助技能，这种固定语言/区域设定可能构成语言/locale 策略上的约束。
The default_prompt contains a very broad invocation phrase and generic task language ('help me', 'workflow', 'practical help') that can match many unrelated user requests. In combination with a proactive productivity-oriented skill, this increases the chance of unintended activation, causing the agent to inject this skill's behavior or context into conversations where it was not explicitly requested.
allow_implicit_invocation: true permits the system to invoke this skill without explicit user selection, but the file does not define clear trigger boundaries or limiting conditions. Because the skill description and prompt are broad, implicit invocation can cause overreach into many work-productivity requests, increasing the risk of undesired execution paths, prompt interference, or accidental handling of sensitive tasks.
The request pattern is vague and underspecified, so the skill may match ambiguous user intents without enough context to ensure safe or relevant execution. This makes the skill more dangerous in practice because its documented purpose is broad already, and a fuzzy trigger expands activation to unrelated or partially related tasks where the produced workflow or analysis may be misleading.
The file states that one skill file is English and another is Chinese, but it does not indicate that the user can choose their preferred language or locale. This can amount to a language/locale policy issue because the documentation implies fixed language variants without describing opt-in or selection behavior.
This Chinese README includes a core behavior description in English, indicating inconsistent language behavior without any statement about user language preference or opt-in. That can violate language/locale expectations because the file does not clarify whether the skill will respond in Chinese, English, or adapt to the user's preference.
