Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only workflow helper with no executable code, persistence, credential handling, or hidden data movement, though its automatic invocation settings are too broad.
Installing this skill should be low risk from a security standpoint because it is guidance-only. Users should be aware that its broad trigger words and implicit invocation may cause it to activate for ordinary productivity or bug-fix requests, so narrowing triggers or requiring explicit invocation would improve predictability.
The description says to use the skill when a user asks for broad concepts like "work-productivity," "proactive," "task," or any practical workflow or artifact, which is too ambiguous for safe routing. This can lead to accidental invocation on ordinary user requests, causing mis-scoping, confusion, and potentially bypassing more specialized or safer skills that should have handled the request.
The trigger list includes very broad, everyday terms such as "task," "needs," and "partners," which can cause the skill to activate in many unrelated conversations. In an agent environment, overbroad activation increases the chance of prompt-routing errors, unintended execution of this skill instead of a more appropriate one, and expansion of the skill's influence beyond its intended scope.
触发关键词包含大量高度通用词汇，如“task”“needs”“partners”“proactive”，并且示例触发句也非常宽泛，容易与普通办公、协作或任务管理对话重叠。这会导致技能在并非目标场景下被误激活，把用户带入不相关流程，进而造成错误自动化、混淆输出或对其他更合适技能的覆盖。
The trigger phrases are broad, generic, and overlap with ordinary productivity requests such as 'help me', 'practical workflow', 'task', and 'needs'. In an agent routing system, this can cause the skill to activate for unrelated user intents, leading to prompt-surface expansion, incorrect tool selection, and increased exposure to downstream unsafe behavior if the skill performs proactive transformations without strong scoping.
The trigger phrases are broad, generic, and partially duplicated from the requirement text, which increases the chance that the skill activates in situations the user did not explicitly intend. In an agentic workflow context, unintended activation can cause the wrong workflow or instructions to be applied, leading to confused execution, unsafe automation, or accidental processing of unrelated tasks.
The trigger keywords and example activation phrases are very broad and generic, including common terms like 'task', 'transform', 'needs', and 'bug fix'. In an agent ecosystem, this can cause unintended activation in unrelated contexts, leading the skill to intercept prompts it was not meant to handle and potentially influence workflow or outputs without clear user intent.
技能描述将适用范围定义为用户提到若干宽泛主题，或“需要实用流程、产物、检查清单、分析或实现支持”时即可使用，这种边界几乎可覆盖大量普通请求。模糊的激活条件会提升误调用概率，使该技能在非预期上下文中介入，降低系统路由准确性并可能影响结果质量与安全审查针对性。
The manifest description and default prompt are broad, vague, and framed to match many generic user requests such as workflow help, analysis, implementation support, or task assistance. This increases the chance of unintended routing or over-invocation, causing the skill to activate in contexts beyond its intended scope and potentially process sensitive user tasks without clear user intent.
Enabling implicit invocation without narrow trigger constraints allows the platform to call this skill automatically based on ambiguous similarity matching. In combination with the broad manifest language, this materially raises the risk of accidental invocation, privilege overreach in multi-skill environments, and unintended exposure of user context to a skill that was not explicitly selected.
The file declares both English and Chinese instruction and guide files, but it does not explain how the user's preferred language is selected. Because language handling is described without an explicit opt-in or choice mechanism, this creates a mild natural-language locale policy concern.
This user-facing README.zh-CN.md is presented as the Chinese version, but substantial instructional content and trigger phrases remain in English. That can effectively force a language choice for users of this locale-specific document without explicit opt-in or explanation.
