Security audit
Security checks for vulnerabilities and agentic risk
This skill is a documentation-only helper for improving error messages, with broad auto-invocation wording but no executable code, persistence, credential access, or hidden behavior.
Installers should understand that this skill may be selected automatically for broad debugging, support, or troubleshooting phrasing. It is low risk as packaged, but publishers should narrow the triggers to explicit error-message improvement requests to reduce unintended activation.
The trigger sentence is so broad and generic that it can match ordinary user requests unrelated to explicitly invoking this skill. That creates a prompt-routing vulnerability where the skill may activate unexpectedly, causing instruction shadowing, incorrect task selection, or untrusted skill content being injected into otherwise normal conversations.
The trigger sentences are broad, generic, and closely resemble ordinary user requests, which can cause the skill to activate outside its intended scope. In an agent environment, this increases the chance of unintended routing or prompt injection surface expansion because normal troubleshooting requests may invoke this skill without clear user intent.
The trigger phrases are broad natural-language requests like 'Help me' and 'I need a practical workflow', which can overlap with ordinary user conversation and cause the skill to activate unintentionally. In an agent setting, over-broad activation can route unrelated requests through this skill, creating prompt-injection surface expansion and unintended processing of user inputs.
The skill description uses broad activation terms like work-productivity, debugging, user feedback, support, and practical workflow, which can cause the skill to trigger on many ordinary requests beyond its narrow purpose. Over-broad routing increases the chance of unintended invocation, causing prompt-scope confusion and potentially exposing unrelated user tasks to skill instructions or artifacts not meant for that context.
The trigger examples are generic and phrased in a way that could match commonplace support or workflow requests, making accidental activation more likely. This is dangerous because broad trigger phrases can let the skill intercept unrelated interactions, reducing routing precision and increasing the risk of irrelevant or misleading assistance being applied in the wrong context.
The trigger section uses very broad, generic keywords such as work-productivity, debugging, support, and troubleshooting without meaningful scope limits. This can cause the skill to activate in many unrelated conversations, increasing the chance it intercepts tasks outside its intended domain and influences outputs unexpectedly.
The example trigger starts with a common expression ('Help me ...'), which is a highly generic conversational pattern. In skill-routing systems, this raises the risk of accidental invocation from normal user phrasing, causing overreach and misapplication of the skill in contexts that only loosely resemble the intended use case.
The skill enables implicit invocation while using a very broad, generic description covering work productivity, debugging, support, analysis, and implementation help. This can cause the agent to auto-select the skill in contexts beyond narrowly scoped error-message improvement, increasing the chance of unintended prompt exposure, inappropriate tool use, or execution of skill instructions in unrelated tasks.
The file descriptions explicitly label English and Chinese instruction variants, but the README does not state how the user's preferred language is selected or that the user can choose. This can create ambiguity around language handling and may violate locale-choice expectations if one version is used by default without opt-in.
该文件整体为中文版本说明，但未见任何提示说明用户可选择其他语言，或该语言约束仅适用于特定区域/受众。按照语言/区域策略要求，若技能面向广泛用户，文档或说明中应提供语言选择、双语指引或明确的适用范围。
This zh-CN skill description embeds English trigger terms and a long English requirement statement, which can effectively bias usage toward English despite the file being localized for Chinese users. The file does not state that users may choose their preferred language or locale for interaction.
