Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only planning skill for product idea validation, with no code execution, persistence, credential access, or destructive behavior found.
Before installing, be aware that this skill may be selected for general startup, SaaS, validation, or prototype requests because its triggers are broad. It appears safe as an advisory workflow skill, but users who want tighter routing may prefer more specific invocation wording or disabling implicit invocation.
The trigger sentences are broad, repetitive, and closely mirror generic product-help requests, which increases the chance that the skill activates for loosely related prompts rather than explicit user intent. In an agent environment, this can cause inappropriate routing, overshadow more suitable skills, and lead to confusing or unintended actions based on a weak match.
The trigger sentences are broad enough to match common product, business, and workflow requests, which can cause the skill to activate outside its intended scope. Over-broad activation is dangerous because it can hijack unrelated user requests, increase prompt-routing errors, and expose users to instructions or workflows they did not explicitly ask for.
The trigger phrases are broad, generic, and partly templated in a way that could cause the skill to activate for loosely related requests rather than clear user intent. In an agent environment, ambiguous activation can lead to incorrect routing, unintended execution of business-planning workflows, or the collection/processing of user context without sufficiently explicit opt-in.
The skill description contains broad activation terms such as business-and-operations, product idea, validation, prototype, and implementation support, which can match many ordinary user requests outside the skill’s intended niche. This increases the chance of unintended invocation and prompt-scope capture, where the skill may activate in unrelated contexts and influence responses without clear user intent.
The trigger keywords are short, generic, and ambiguous, especially terms like validation, prototype, saas, and startup. These keywords are common across many benign conversations, so they can cause accidental routing to this skill and create overreach into tasks the skill was not designed to handle.
The example trigger sentences use everyday phrasing like help me and I need a practical workflow, which are common across a wide range of requests. Because they pair generic request language with only lightly scoped domain text, they normalize broad matching behavior and make unintended activation more likely.
该技能文件整体以中文编写，且未见任何说明表明用户可选择其他语言或按用户偏好输出。根据规则，若技能强制特定语言而没有用户 opt-in 或语言选择机制，可能构成语言/locale 策略问题。
The skill description includes broad trigger terms such as business-and-operations, product idea, validation, prototype, and saas without clear scope boundaries. This can cause unintended activation during ordinary discussion, leading the agent to apply this workflow in contexts the user did not request, which increases the risk of confusing, irrelevant, or policy-bypassing behavior through over-selection of the skill.
The trigger section lists only generic keywords and example invocations, but does not define required context, disambiguation checks, or non-trigger cases. In a routing system, this ambiguity can cause accidental invocation across many normal startup or product conversations, reducing user control and potentially steering outputs toward a prepackaged workflow the user did not intend.
The default prompt is extremely broad and generic, covering common product, business, workflow, checklist, and analysis requests. This increases the chance the skill is implicitly selected for ordinary conversations where the user did not intend to invoke it, which can cause scope confusion, prompt hijacking opportunities through over-triggering, and unintended access to the skill's behavior.
Enabling implicit invocation without any activation constraints allows the platform to auto-select this skill based on loosely related user queries. In a broad domain like product help, this creates a meaningful risk of accidental invocation, unintended handling of user tasks, and abuse via crafted prompts that cause the skill to engage outside its intended scope.
The file presents Chinese instructional structure alongside English trigger phrases without clarifying language selection or requiring user preference. This can confuse users and systems about whether activation text is intended as operational syntax, increasing the chance of mistaken invocation or user misunderstanding in multilingual contexts.
No suspicious patterns detected.
