Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only product validation planning skill with broad triggers but no hidden execution, credential access, persistence, or destructive behavior.
Before installing, be aware that this skill may be invoked for broad product, startup, SaaS, or validation wording. It appears safe as an advisory planning aid, but users should confirm they actually want a product-validation workflow when it activates.
The trigger phrases are so generic that they can match many ordinary product, startup, workflow, or validation requests that do not specifically require this skill. Over-broad activation can cause the agent to invoke the wrong skill, leading to unintended behavior, reduced user control, and expanded exposure of the skill in contexts where it was not explicitly requested.
The trigger examples are broad, generic, and partially malformed, which increases the chance that the skill activates for loosely related requests instead of clearly scoped product-validation tasks. In an agent environment, ambiguous activation can cause unintended routing, prompt collisions with other skills, or disclosure of irrelevant business guidance in contexts where the user did not explicitly request this workflow.
The trigger phrases are broad, generic, and closely resemble normal user requests such as asking for help with product ideas, validation, prototypes, or workflows. This increases the chance the skill will activate unintentionally in unrelated contexts, causing misrouting, prompt interference, or unexpected handling of user inputs beyond the intended scope.
The skill description is broad enough to match many ordinary business, product, or implementation requests that may not specifically require this skill. Over-broad routing can cause inappropriate invocation, leading the agent to apply the wrong workflow, make unnecessary assumptions, or expose unrelated context and files to the skill unnecessarily.
The trigger keywords are highly generic terms used across a wide range of harmless and unrelated user requests, which increases the chance of accidental activation. This can degrade routing integrity and cause the skill to intercept queries outside its intended scope, potentially influencing outputs or consuming context that should remain with a more appropriate skill.
The trigger section uses broad terms like 'product idea', 'validation', 'prototype', 'saas', and 'startup', which can overlap with many ordinary user conversations. This can cause unintended skill activation, leading the agent to route users into a business-planning workflow when they did not explicitly request it, increasing the chance of inappropriate context capture or irrelevant automated actions.
The default prompt invokes the skill with a very broad phrase covering business, operations, product ideas, validation, prototyping, SaaS, workflows, and implementation support, without clear boundaries on when it should trigger. Combined with allow_implicit_invocation: true, this increases the chance of unintended or over-broad activation, causing the agent to route unrelated user requests into this skill and potentially expose users to unintended automation or outputs.
This file is entirely presented in Simplified Chinese and does not indicate that the user can choose another language or locale. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale restriction is documented and justified.
文件名和主体内容以中文呈现，但 L04、L11 等说明中混入英文业务术语与英文长句，整体未说明是否应根据用户偏好切换语言，也未提供语言选择。这可能构成默认施加特定语言/语言混用方式的自然语言策略问题。
