Security audit
Security checks for vulnerabilities and agentic risk
This is a low-risk error-message workflow skill with no executable code, credentials, persistence, or data exfiltration behavior, though its activation wording is broader than ideal.
This skill is reasonable to install if you want help rewriting or structuring clearer error messages. Be aware it may trigger too often for general debugging or support prompts because implicit invocation is enabled with broad keywords; review generated outputs before applying them to production user-facing copy.
The trigger sentence is so generic that it can match ordinary user language and cause the skill to activate unintentionally. In an agent setting, over-broad activation can route unrelated requests into this workflow, leading to incorrect handling, prompt-scope confusion, or unintended disclosure of user context into the wrong skill path.
The trigger sentence is written as a broad natural-language request ('Help me ...') that could match many ordinary user prompts and cause the skill to activate unintentionally. In a skill-routing system, overly broad activation increases the chance of context-inappropriate invocation, which can confuse users, override better-matched skills, or inject irrelevant workflow steps into unrelated conversations.
The phrase 'I need a practical workflow for ...' is generic and lacks scope constraints, so it may match a wide variety of unrelated requests that happen to mention workflow or support. This ambiguity can lead to accidental triggering and misrouting, especially because the skill's domain spans broad terms like debugging, support, and user feedback.
The trigger phrases are broad enough to match common support and productivity requests, which can cause the skill to activate outside its intended scope. In an agent environment, overscoped activation can route unrelated user inputs into this skill, creating prompt-injection exposure, incorrect task handling, or unintended disclosure of user context to an unnecessary workflow.
The skill description contains very broad invocation conditions such as general productivity, debugging, support, and workflow requests. This can cause the skill to be activated for many ordinary conversations outside its narrow purpose, increasing the chance of unintended routing, prompt-scope expansion, and inappropriate reliance on the skill in contexts where it was not meant to operate.
The trigger examples use generic phrases like asking for a practical workflow or help without enough domain-specific constraints. These broad examples may spur accidental activation on common requests, causing over-selection of this skill and potentially displacing more appropriate skills or base-model handling.
The skill description uses very broad categories like work-productivity, debugging, user feedback, and support, which are common across many unrelated user requests. This can cause the skill to activate in contexts it was not specifically designed for, increasing the chance of incorrect routing, unintended prompt injection exposure from unrelated content, or unreviewed behavior being applied too widely.
The keyword triggers are highly generic terms that frequently appear in normal conversation, making accidental invocation likely. Over-broad keyword activation can route arbitrary user requests into this skill, which reduces isolation between skills and may create unsafe or confusing behavior when the skill is applied outside its intended scope.
The default prompt is vague and broadly scoped, which can cause the agent to activate for loosely related requests and operate outside a narrowly defined error-message-improvement task. In combination with implicit invocation, this increases the chance of unintended use, prompt cross-triggering, or the agent handling requests with insufficient task boundaries.
Enabling implicit invocation without tight activation criteria allows the skill to be invoked automatically for broad categories like debugging, support, or workflow assistance. This can lead to overreach, accidental triggering, and unsafe delegation of tasks the skill was not explicitly designed or reviewed to handle.
This file is labeled as a Chinese README, but key descriptive and trigger content is written in English, which effectively imposes a language choice without explicit user opt-in. The policy requires offering a language/locale choice or clearly documenting and justifying the locale constraint.
This Chinese skill file presents trigger keywords and example invocations primarily in English, which can impose a language expectation without explicit user opt-in or language selection guidance. The file does not state that users may interact in Chinese or choose their preferred language.
