Security audit
Security checks for vulnerabilities and agentic risk
This is a low-risk planning skill for product validation, with broad activation wording but no code execution, credential access, persistence, or hidden data behavior.
Installers should expect a product-validation planning assistant. Review the broad implicit trigger behavior if you have many business or product skills installed, because this one may activate for loosely related startup, SaaS, prototype, or validation prompts.
The trigger sentence is very broad and resembles ordinary help-seeking language, which can cause the skill to activate in situations far beyond its intended niche. Over-broad activation increases the chance of unintended routing, user confusion, and prompt-scope hijacking where generic requests are steered into this skill without clear user intent.
The invocation description uses a generic 'I need a practical workflow' pattern without constraining the subject matter, making it likely to overlap with many unrelated user requests. In agent environments, this can lead to accidental skill selection and inappropriate handling of tasks that were not meant for a business/product-validation planner.
The trigger phrases are broad enough to activate on common business, product, validation, prototype, or startup requests, which can cause unintended routing of user prompts to this skill. In an agent ecosystem, ambiguous invocation expands the skill’s effective authority surface and can lead to misapplication of its workflow, especially when user intent is only loosely related.
The skill description and activation guidance are broad enough to match many ordinary business, product, and implementation requests that may not actually require this specialized skill. Over-broad routing can cause the agent to invoke the wrong skill, crowd out safer or more appropriate skills, and produce misleading outputs based on assumptions that do not fit the user's intent.
The keyword list uses vague, high-collision terms like 'prototype', 'saas', 'validation', and 'product idea' without qualification, making accidental activation likely across many unrelated conversations. In a skill-routing system, this can misdirect user requests into an ill-fitting workflow, leading to irrelevant guidance, hidden assumptions, or bypass of more suitable domain-specific skills.
The usage guidance describes when to use the skill in terms that are expansive and imprecise, making the activation boundary unclear. This can lead to accidental invocation for loosely related requests, increasing the attack surface and causing the skill to influence conversations it was not meant to handle.
The trigger keywords are broad and overlap with common product and business conversations, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of unintended prompt injection exposure, irrelevant workflow takeover, or user confusion when a general discussion is incorrectly routed into this skill.
The default prompt and skill description are broadly worded around common business, product, validation, prototype, and implementation tasks, while implicit invocation is enabled. This creates a real risk that the agent will be auto-selected in loosely related conversations and may steer users into this skill without sufficiently precise trigger boundaries.
The trigger sentence starts with a very broad everyday phrase ('Help me') tied to a large topical area, which can cause the skill to activate on many unrelated user requests. Overbroad activation increases the chance of unintended routing, prompt-context injection into unrelated tasks, and unsafe delegation where the user did not explicitly ask for this business-validation workflow.
This trigger is ambiguous because it requests a 'practical workflow' without enough constraints to distinguish this skill from many other planning, consulting, or operations skills. Ambiguous activation can misroute user requests, causing the agent to invoke the wrong capability and potentially expose the user to irrelevant instructions, incorrect assumptions, or unnecessary context mixing.
The file list states that SKILL.md contains English skill instructions, which suggests a default language constraint in the skill materials. While Chinese documentation is also present elsewhere, this README does not explicitly state that users can choose their preferred language or locale.
This file is labeled as a Chinese README, but key user-facing content including the title, requirement description, workflow description, keywords, and trigger phrases remain in English. That creates a language/locale policy concern because the skill effectively forces English content on users of the zh-CN variant without any opt-in or documented justification.
该文件为 SKILL.zh-CN.md，整体内容仅以简体中文提供，未见对用户语言偏好的选择说明或可切换语言提示。若该技能面向通用用户而非明确的区域性场景，这可能构成语言/区域策略上的默认强制。
