Security audit
Security checks for vulnerabilities and agentic risk
This is a product-validation planning skill with broad triggers, but its behavior is disclosed, low-impact, and limited to guidance and planning artifacts.
Before installing, be aware that generic product or startup requests may invoke this skill automatically. Its inspected content is limited to product-validation guidance and does not add executables, persistence, credential access, or destructive behavior.
The trigger sentence begins with a very broad everyday phrase ('Help me') and then appends the requirement text, making activation criteria loose and easy to match unintentionally. In an agent-routing context, this can cause the skill to activate for unrelated business or product questions, leading to inappropriate handling, prompt collisions, or routing away from safer or more relevant skills.
The trigger sentences are generic and map to common product and business language, which increases the chance that the skill is invoked for loosely related requests rather than explicit user intent. In an agent environment, over-broad activation can route sensitive or unrelated conversations into this skill unexpectedly, causing prompt/context confusion and reducing control over which instructions are applied.
The trigger phrases are broad enough to match ordinary user requests about practical workflows or product ideas, which can cause this skill to activate when the user did not explicitly intend to use it. Over-broad activation increases the chance of inappropriate routing, unexpected instruction injection from the skill, or interference with more relevant skills during normal conversations.
The skill description is broad enough to activate on many ordinary product, business, or planning requests without strong boundary conditions. This can cause inappropriate routing or over-invocation of the skill, leading the agent to apply specialized behavior when a more precise or safer skill should have been selected.
The trigger keywords and example phrases are highly generic terms such as 'validation', 'prototype', 'saas', and 'startup', which are common across many unrelated user requests. In context, this increases the chance of accidental activation and prompt-scope capture, where the skill may intercept broad classes of conversations beyond its intended niche.
The description defines a very wide usage scope spanning business operations, product ideas, validation, prototypes, and SaaS support without clear boundaries for when the skill should or should not be invoked. This ambiguity increases the chance of misrouting, accidental invocation, and overreach into requests that need different expertise or stricter controls.
The trigger keywords are broad and generic business terms like "validation", "prototype", and "saas", which can cause the skill to activate during ordinary product discussions unrelated to this specific workflow. Over-broad activation can route users into the wrong skill, producing irrelevant guidance, suppressing better-matched skills, or causing unintended processing of business context.
The default prompt is highly generic and pairs with implicit invocation, which can cause the skill to activate for broad, loosely related user requests. This increases the chance of unintended routing, prompt-surface expansion, and the skill influencing conversations outside its intended scope, especially in mixed-agent environments.
The trigger sentence is ambiguous because it uses a generic request pattern ('I need a practical workflow for ...') without clear boundaries on when the skill should be invoked. This increases the chance of overbroad matching across many operational or planning requests, which can degrade routing integrity and cause the agent to apply this skill outside its intended domain.
This file is presented entirely as a Simplified Chinese localized README, but it does not state that language choice is optional within the document itself. Because the skill documentation here assumes a fixed locale without explicit user opt-in or a documented justification, it may conflict with language-choice policy expectations.
L48-L50 的示例触发句全部使用英文，而文件主体为中文，且未说明技能是否要求用户以英文触发或是否支持语言选择。若该技能在实际使用中隐含要求特定语言而未提供用户选择，可能构成语言/locale 政策上的不明确约束。
