Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only product validation planning skill with broad activation wording but no hidden code, persistence, credential access, or destructive behavior.
Install this if you want structured help with product idea validation. Be aware that its broad keywords and implicit invocation may cause it to appear for some general startup or prototype requests, so invoke a different skill explicitly if you need narrower help.
The trigger sentence begins with a broad, natural-language activation pattern ('Help me ...') that can match many ordinary user requests outside the intended scope. This increases the chance of accidental skill invocation, causing scope confusion and potentially routing unrelated conversations into business-planning behavior without clear user intent.
The invocation guidance lacks precise boundaries and specificity, making it unclear when the skill should or should not be selected. In an agent environment, ambiguous routing can cause this skill to intercept common startup, operations, or general planning requests, leading to inappropriate tool use or cross-context prompt capture.
The trigger sentence is broad enough to match ordinary help-seeking requests about products, workflows, or validation, which can cause the skill to activate outside narrowly intended contexts. Overbroad activation increases the chance of prompt routing mistakes, unnecessary exposure of the skill's instructions, or unintended influence over unrelated conversations.
The trigger phrases are broad enough that ordinary requests about business operations, product ideas, validation, prototypes, or SaaS could activate the skill unintentionally. In an agent environment, over-broad activation can cause the wrong skill to take control, produce irrelevant outputs, or override a more appropriate workflow, which becomes a security and reliability problem when skills can influence downstream actions.
The skill description uses broad, generic invocation terms such as business-and-operations, practical workflow, artifact, checklist, analysis, and implementation support. This can cause the router to select the skill for many unrelated requests, leading to inappropriate activation, degraded task routing, and possible misuse of the skill outside its intended product-validation scope.
The trigger keywords include ambiguous and high-frequency terms like validation, prototype, and startup without qualifiers. These broad triggers increase the chance of accidental invocation for unrelated contexts, which can misroute user requests and make downstream behavior less predictable.
The activation description is broad enough to match many normal business, product, or startup discussions, which can cause the skill to trigger outside its intended scope. Over-broad triggering increases the chance of unwanted instruction injection into unrelated conversations and can override more appropriate, narrower skills.
Keywords like 'validation', 'prototype', 'saas', and 'startup' are generic and appear frequently in ordinary conversations, making accidental activation likely. If triggered unintentionally, the skill may steer responses toward its workflow even when the user's actual need is different, creating prompt-routing and scope-control risk.
The default prompt is very broad and maps to a wide range of business, product, prototype, and implementation-related requests without clear activation boundaries. This increases the chance of the skill being invoked for loosely related prompts, causing over-collection of context, unintended delegation, or inappropriate influence over user workflows.
Enabling implicit invocation while providing only a broad description and trigger phrase makes the skill eligible to activate without explicit user consent in many ambiguous contexts. In a skill that offers planning, analysis, and implementation support, this can lead to unintended tool routing, excessive trust in generated business guidance, and confusion about when the specialized skill is acting.
The phrase 'I need a practical workflow for ...' is vague and lacks firm scoping boundaries, so the skill may activate for many generic process-oriented requests. In an agent environment, ambiguous triggers can lead to mis-selection of the skill, producing irrelevant outputs and increasing the attack surface for prompt-routing manipulation through loosely related phrasing.
This README is a Chinese-localized user document and references both English and Chinese files, but within this file there is no statement that users may choose their preferred language. Because natural-language policy checks apply to all file types, presenting a localized experience without explicit opt-in can be a locale policy concern.
The file is a zh-CN skill document, but the activation description and examples embed substantial English phrases and keywords without stating whether the skill should respond in Chinese, English, or according to user preference. This may impose a language expectation without explicit user opt-in.
