Security audit
Security checks for vulnerabilities and agentic risk
This skill is a plain documentation workflow for improving error messages, with no executable code or hidden privileged behavior.
Install this if you want a lightweight helper for making error messages clearer. Be aware it may activate on broad support or debugging phrasing, so explicitly invoke a more specific skill when your task is not about error-message wording or troubleshooting guidance.
The trigger text is extremely broad and overlaps with ordinary user phrasing, which can cause the skill to activate in situations far beyond its intended scope. In an agent environment, overly generic activation conditions can misroute unrelated requests into this skill, leading to prompt-scope confusion, degraded handling, and increased exposure to adversarial or irrelevant inputs.
The trigger phrases are broad enough to match ordinary support or debugging requests, which can cause the skill to activate when the user did not explicitly intend to use it. In an agent ecosystem, this creates a routing and prompt-scope risk: the skill may capture general conversations and influence outputs more often than expected, increasing the chance of unintended behavior or abuse by indirect invocation.
The trigger phrases are broad enough to match common support and productivity requests, which increases the chance the skill is invoked when the user did not explicitly intend to use it. In an agent environment, unintended invocation can misroute user input, cause incorrect workflow selection, and amplify the influence of a skill on unrelated tasks.
The skill description is very broad and includes generic categories like work-productivity, debugging, support, and user feedback without strong scope boundaries. This can cause the skill to activate for loosely related requests, increasing the chance of inappropriate routing, prompt interference, or the skill being applied in contexts it was not designed to handle.
The trigger keywords are short, generic, and high-frequency terms that commonly appear in many unrelated conversations. This raises the risk of accidental invocation, which can misroute tasks, introduce irrelevant instructions into the agent workflow, and create opportunities for prompt-scope confusion.
The skill description says to use it for broad categories like work-productivity, debugging, user feedback, and support without defining clear boundaries or exclusion criteria. That can cause the agent to invoke this skill in many unrelated contexts, leading to inappropriate handling of user requests, skill overshadowing, and reduced reliability of routing or downstream safety controls.
The trigger keywords include very generic terms such as debugging, support, troubleshooting, and user feedback, which are common across many unrelated tasks. Overly generic triggers increase accidental activation and can make this skill capture requests better handled by more specific skills, creating confusion, misrouting, and possible bypass of intended workflow specialization.
The skill enables implicit invocation while providing a very broad activation description tied to common themes like productivity, debugging, support, and analysis. This increases the chance the agent will invoke the skill in situations the user did not clearly intend, potentially causing unintended prompt routing, over-collection of user context, or inappropriate influence over responses.
The README lists separate English and Chinese instruction and guide files, but it does not state how the user's language preference is selected or whether the user can opt in to a locale. Because locale handling is described in natural language and no choice mechanism is documented here, this may conflict with language/locale policy expectations.
This is a Chinese-language README, but the activation examples are presented only in English and effectively prescribe English phrasing for use. That can constitute a language/locale policy issue because the file does not offer a Chinese alternative or explain why English-only triggers are required.
