Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only skill for improving error messages; its triggers are broad but no hidden code execution, credential access, persistence, or destructive behavior was found.
Before installing, be aware that this skill may be invoked by broad support or debugging wording even when you only wanted general help. It appears safe from a security standpoint, but users should prefer explicit invocation when they want error-message rewriting or related troubleshooting copy.
The trigger sentence is so broad and natural-language-like that it can match ordinary user requests rather than explicit invocation intent. This can cause unintended activation of the skill in unrelated conversations, leading to prompt-routing errors, user confusion, and possible exposure of internal support or debugging workflows when they were not requested.
The trigger sentences are generic enough to match ordinary requests about help, workflows, support, or debugging, which can cause the skill to activate in contexts far beyond its intended scope. Over-broad activation increases the chance of unintended prompt injection surface, misrouting, or the skill taking over unrelated user tasks without clear user intent.
The trigger phrases are broad enough to match common, non-specific user requests such as general help with productivity, debugging, or support. In an agent skill system, this can cause unintended activation and route ordinary conversations through this skill without clear user intent, increasing the chance of inappropriate instructions, prompt-surface expansion, or interference with safer/default behaviors.
The skill description is scoped to very common terms like work-productivity, debugging, user feedback, and support, which creates a real risk of unintended invocation in many unrelated conversations. While this is not a code-execution issue, over-broad routing can cause the wrong skill to activate, leading to irrelevant guidance, user confusion, and potentially unsafe automation if downstream workflows act on the mismatch.
The keyword triggers are generic and cover broad operational language like debugging, support, and troubleshooting without clear boundaries. In an agent environment, this can cause frequent false activations and misrouting, which is more dangerous here because the skill is designed to produce artifacts and workflows that may steer user actions based on an incorrect interpretation of intent.
The example trigger phrases are so broad that they normalize invocation from everyday requests rather than clearly bounded error-message improvement tasks. This increases the chance that orchestrators or users invoke the skill in situations where it is not appropriate, producing low-quality or misleading outputs and increasing operational risk through incorrect assistance.
The skill description defines activation conditions so broadly—covering work-productivity, debugging, support, and user feedback—that it lacks a clear boundary for when the skill should or should not be used. Overbroad activation increases the chance of accidental invocation, which can interfere with more appropriate skills, dilute safety controls, or cause the model to follow an irrelevant workflow in sensitive troubleshooting contexts.
The trigger section uses very broad generic keywords such as "debugging", "support", and "user feedback", plus example invocations that overlap with ordinary user requests. This can cause the skill to activate in many unrelated contexts, creating prompt-routing confusion and potentially exposing the model to unintended instruction precedence or irrelevant workflow injection.
The default prompt is broadly phrased and can trigger the skill for a wide range of loosely related requests without clear boundaries. In an implicit-invocation setting, this increases the chance of unintended activation, causing the agent to apply this skill in contexts where its guidance is not appropriate or where it could override more precise handling.
The invocation guidance does not define when the skill should and should not run, leaving trigger scope ambiguous. In an agent environment, this increases the chance of accidental or overbroad routing, where the skill may activate on loosely related requests and produce actions or advice outside the intended requirement boundary.
The file declares separate English and Chinese instruction and guide files, but does not state how the user's preferred language is selected or whether language choice is optional. This can create a locale-policy concern if the skill defaults to a language without explicit user opt-in.
This file is named as a Chinese README, but key descriptive content and user-facing trigger phrases remain in English. That can amount to forcing a language choice on users of the localized document without explicitly offering an alternative or documenting the constraint.
