Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only product validation planning skill with some broad activation wording but no hidden execution, data access, persistence, or privilege behavior.
Installers should understand that this skill is low-risk and planning-oriented, but its trigger metadata should ideally be narrowed so it activates only for explicit product idea validation, MVP testing, customer discovery, or positioning-planning requests.
The activation examples are ambiguous and truncated, and they do not clearly distinguish when this skill should be invoked versus general business or brainstorming assistance. That ambiguity increases the chance of accidental activation across common conversations, which can override more appropriate skills or inject irrelevant workflow guidance into unrelated tasks.
The trigger sentence is broad enough to match many ordinary requests about help, workflows, or product ideas, which can cause the skill to activate outside its intended scope. Over-broad activation can hijack unrelated user interactions, leading to unintended instruction injection into sessions and reducing the reliability of skill routing.
The trigger phrases are broad generic terms like "validation," "prototype," and "saas," plus imperative examples that could match many unrelated user requests. In an agent-routing system, this increases the chance of unintended invocation, causing the skill to handle prompts outside its intended scope and potentially expose downstream workflows, tools, or planning behaviors in inappropriate contexts.
The skill description is broad enough to match many common business, product, and implementation requests, which raises the chance of unintended invocation. Over-broad routing can cause the wrong skill to activate, leading to inappropriate instructions, unexpected data exposure to the skill context, or bypass of more specific/safe skills.
The trigger keywords are highly generic terms such as 'validation', 'prototype', 'saas', and 'startup', which commonly appear in unrelated requests. This increases the risk of accidental invocation and prompt-routing confusion, allowing the skill to intercept requests outside its intended scope and potentially influence outputs inappropriately.
技能描述中的适用范围覆盖 business-and-operations、product idea、validation、prototype、saas 等大类需求，但没有清晰界定边界或排除条件，因此调度器可能在相邻但不匹配的场景中错误选择该技能。这样的模糊性会扩大技能调用面，增加误用、错误自动化和对用户请求的非预期重写风险。
触发关键词包含 business-and-operations、validation、prototype、saas、startup 等高度通用词，容易与大量正常对话重叠，导致技能在用户并未明确请求该能力时被误触发。误触发会把后续回答引向固定的产品验证工作流，造成上下文偏移、错误建议或压制更合适的技能/系统行为。
The default prompt uses a broad invocation phrase ('Use $product-validation-planner to help me...') tied to a wide set of business/product requests, without clear trigger boundaries or safety constraints. In systems with implicit invocation enabled, this ambiguity can cause the skill to activate in contexts the user did not clearly intend, increasing the risk of prompt routing mistakes, over-collection of user context, or unintended execution of downstream planning behavior.
The invocation examples and trigger sentences do not clearly specify when the skill should and should not activate, creating ambiguous routing behavior. In agent systems, unclear boundaries can lead to accidental activation on common business or planning requests, causing unintended tool use, poor task selection, and possible prompt-scope interference with other skills.
The trigger sentence is broad enough to match ordinary user phrasing about needing a practical workflow, which can cause the skill to activate outside its intended scope. Misrouting is risky because it can override more appropriate skills or inject product-validation workflows into unrelated conversations, reducing reliability and potentially causing unsafe or misleading guidance in edge cases.
This file is presented as a Chinese README, but substantial user-facing content including the core description and trigger phrases is in English. That creates an implicit language constraint or inconsistent locale experience without stating that the user can choose their preferred language.
该技能文件为 SKILL.zh-CN.md，整体内容固定为简体中文语境，未见向用户提供语言选择、回退机制或说明仅在用户选择中文时使用。根据规则，若技能隐含强制特定语言而没有用户 opt-in，属于自然语言层面的组织政策风险。
No suspicious patterns detected.
