Security audit
Security checks for vulnerabilities and agentic risk
This skill is a low-impact product-validation planning guide with broad activation wording but no hidden execution, credential access, persistence, or destructive behavior.
This skill is reasonable to install if you want help structuring product validation work. Be aware that its activation phrases are broad, so it may appear for general product, SaaS, startup, or prototype conversations even when a narrower skill might be better.
The invocation guidance lacks precise boundaries and includes generic phrasing like 'Help me' and 'I need a practical workflow,' which overlaps with many ordinary requests. In an agent environment, this can lead to accidental or excessive activation, misrouting user intent, and increasing the attack surface for prompt/skill confusion.
The trigger sentence is extremely broad and resembles normal user help-seeking language, which can cause the skill to activate outside its intended scope. Over-broad activation increases the chance of untrusted or unrelated requests being routed into this skill, producing inappropriate guidance or overriding a more suitable specialized skill.
The trigger phrases are broad enough to match common business/product queries, which can cause the skill to activate when the user did not explicitly intend to use it. In an agent system, unintended invocation can lead to irrelevant workflow execution, context hijacking, or accidental exposure of user inputs to skill-specific processing, even though this file itself does not contain direct code-execution behavior.
The skill description is scoped to very broad categories like business operations, product ideas, validation, prototypes, and implementation support, which can match many ordinary user requests. Over-broad routing increases the chance this skill is invoked when a more specific or safer skill should handle the task, causing prompt/skill confusion and unintended authority over loosely related workflows.
The trigger keywords and example phrases are highly generic, including terms such as 'validation', 'prototype', 'saas', and 'startup', which are common across many unrelated requests. This makes accidental or excessive invocation more likely, creating misrouting risk and reducing trust boundaries between skills.
The manifest description says to use the skill for broad topics like business-and-operations, product idea, validation, prototype, and saas, which creates ambiguous routing boundaries. In multi-skill environments, this can lead to unintended invocation and prompt-context hijacking of benign user requests that should be handled by a more specialized skill.
The skill file presents the operational instructions and expected interaction entirely in Chinese, while the trigger examples and domain description include English content, but there is no statement offering the user a language or locale choice. That can amount to a language policy violation if the skill implicitly constrains responses to Chinese without opt-in.
The trigger keywords and example invocations are broad enough to match many ordinary product or startup conversations, which can cause the skill to activate outside its intended scope. Over-broad routing increases the chance that the agent applies the wrong workflow, suppresses better-matched skills, or produces irrelevant guidance in contexts involving business decisions.
The skill enables implicit invocation (allow_implicit_invocation: true) without any visible narrowing conditions, triggers, or scope constraints. This can cause the agent to invoke the skill in broader contexts than intended, increasing the chance of unsolicited use, prompt-scope confusion, or accidental exposure of the skill’s instructions and behavior in unrelated conversations.
The usage signals and trigger descriptions do not define clear activation boundaries, so the orchestrator may invoke the skill for loosely related business, prototype, or SaaS requests. In this context, the skill is not directly code-executing or privilege-bearing, which lowers severity, but ambiguous routing still creates a real security and safety issue by broadening the skill's reach beyond intended scenarios.
The trigger sentence is broad enough to match ordinary user requests about product ideas, workflows, or startup help without clear boundaries, which can cause unintended invocation of this skill. Over-broad activation is dangerous because it may route users into an unrelated or lower-priority workflow, increasing the chance of inappropriate actions, confused delegation, or prompt-surface expansion across benign conversations.
No suspicious patterns detected.
