Security audit
Security checks for vulnerabilities and agentic risk
This skill is a low-risk planning aid for product validation, with only a minor risk of being invoked too broadly.
Before installing, be aware that the skill may activate on broad product, startup, prototype, or validation wording. It appears safe to use for product-validation planning, but users who want tighter routing should invoke it explicitly with $product-validation-planner.
The activation examples are ambiguous and do not clearly bound when the skill should run, which can cause accidental invocation from common startup, prototype, or workflow-related requests. In an agent environment, ambiguous routing can expose users to incorrect automation paths, suppress better-matched skills, or make prompt behavior less predictable.
The trigger sentence is so generic that it can match ordinary user requests for help with product ideas or workflows, causing the skill to activate outside its intended scope. Over-broad activation increases the chance of unintended routing, prompt interference, and the skill being invoked when another safer or more appropriate capability should handle the request.
The trigger phrases are broad and map to very common user intents such as needing 'a practical workflow' or help with product ideas. This increases the chance the skill is invoked in situations where the user did not explicitly request it, causing unintended routing and possible overshadowing of more appropriate skills or system behavior.
The file labels itself as the Chinese user guide and explicitly maps English and Chinese documentation variants, but it does not indicate any user choice or opt-in for language selection. This can violate language/locale policy if the skill experience defaults users into a specific locale without offering an option.
The skill description is extremely broad and matches common product, business, prototype, and SaaS-related requests. That can cause the skill to activate in many unrelated contexts, increasing the chance it overrides more appropriate skills or injects planning behavior where it was not explicitly intended.
The trigger keywords are generic terms like 'validation', 'prototype', 'saas', and 'startup', which are common across many benign conversations and unrelated skills. Overly generic triggers create ambiguous routing, making accidental invocation more likely and reducing control over when this skill is applied.
The description says to use the skill for broad categories like business-and-operations, product idea, validation, prototype, and saas, which are expansive domains rather than precise invocation criteria. This ambiguity increases the chance of incorrect tool selection and context hijacking, where the assistant follows this skill when a narrower or safer skill would be more appropriate.
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 activation can steer unrelated requests into this workflow, creating prompt-routing errors, irrelevant guidance, and reduced reliability of downstream agent behavior.
The default prompt and description are broad enough to match a wide range of common product, business, workflow, and implementation requests. Combined with allow_implicit_invocation=true, this can cause the skill to be invoked unexpectedly, exposing users to unintended prompt steering or data flow into the skill when they did not explicitly request it.
The activation examples do not define clear scope boundaries, required conditions, or exclusions, so the orchestrator may invoke the skill for a wide range of generic business or planning requests. In a multi-skill environment, this ambiguity can lead to misrouting, unnecessary exposure of user context to the wrong skill, and degraded safety controls because the skill is selected outside its intended use case.
The trigger sentence is so generic that ordinary user requests about product ideas, SaaS, or practical workflows could activate this skill unintentionally. Over-broad activation increases the chance of routing unrelated conversations into this skill, which can cause inappropriate behavior, prompt-surface expansion, and interference with more suitable skills.
The example trigger phrases use vague everyday language like 'Help me' and 'I need a practical workflow', which are too general to safely distinguish this skill from normal user requests. Such examples encourage broad matching and can cause unintentional activation during ordinary assistance scenarios.
The file is written entirely in Chinese and does not indicate that responses should follow the user's language preference, which can cause forced language switching. While not a direct code-execution risk, this can degrade usability, cause misunderstandings, and make safety-critical clarifications less effective if the user's preferred language is different.
No suspicious patterns detected.
