Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only product validation planning skill with broad activation wording but no evidence of hidden code, persistence, credential access, or destructive behavior.
This skill is reasonable to install if you want help validating product or startup ideas. Be aware that its activation terms are broad, so users or maintainers should prefer explicit invocation or narrow the trigger text if accidental activation would be disruptive.
The skill description is extremely broad and includes common business terms like product idea, prototype, and implementation support, which can cause the skill to activate for many unrelated requests. Overbroad invocation increases the chance that the wrong skill handles a user task, leading to inappropriate guidance, unsafe automation paths, or instruction shadowing in multi-skill environments.
The trigger keywords are highly generic (business-and-operations, product idea, validation, prototype, saas, startup) and lack disambiguation or scope limits. In a skill-routing system, such generic triggers can cause accidental invocation across a large share of normal conversations, reducing routing integrity and potentially overriding more appropriate specialized skills.
The trigger sentence is so broad and awkwardly phrased that it can match many unrelated requests containing common help-seeking language rather than a clearly scoped product-validation intent. Overbroad activation can cause the wrong skill to intercept user requests, leading to irrelevant guidance, confused routing, or accidental handling of tasks outside the skill’s intended domain.
This trigger uses a generic request pattern ('I need a practical workflow for ...') that is common across many benign user intents, making false activation likely. Because the skill is positioned broadly around business, product ideas, validation, prototypes, and implementation support, an overbroad trigger increases the chance of misrouting unrelated requests into this skill’s workflow.
The README defines 'Trigger sentences' using generic phrasing like 'Help me' and 'I need a practical workflow', which overlaps with common everyday speech and does not clearly constrain when this skill should activate. It also lacks negative examples or scope boundaries to distinguish valid invocations from unrelated requests.
The trigger phrases are broad enough that this skill could be invoked for loosely related requests, increasing the chance of inappropriate activation and unintended handling of user tasks. In an agent ecosystem, ambiguous invocation boundaries can cause misrouting, override more appropriate skills, or expose users to outputs that were not intended for their context.
The description defines a very large activation scope covering multiple domains and artifact types without specifying exclusion criteria. This ambiguity can cause the skill to be invoked too often, letting it influence conversations outside its intended scope and potentially override more appropriate skills or baseline handling.
The trigger keywords are very broad (for example, business-and-operations, product idea, validation, prototype, saas, startup), so the skill may activate during ordinary product or business conversations that do not actually need this workflow. Over-broad activation increases the chance of inappropriate skill injection, confusing routing, and unintended disclosure or shaping of responses in contexts where the user did not request this capability.
The default prompt uses a broad, natural-language invocation phrase tied to a wide set of business and product-related requests, which can cause the skill to activate in contexts the user did not explicitly intend. Because implicit invocation is also enabled, this increases the risk of over-broad routing, accidental data exposure to the skill, or unintended influence over user workflows.
The file lists separate English and Chinese instruction and guide files, but does not explain how the user's preferred language is selected or whether language choice is user-driven. This can create an implicit locale policy without clear opt-in or selection behavior.
This user-facing markdown is entirely in Chinese for headings and usage guidance, but does not state that language is optional or that the skill is intended only for Chinese-speaking users. Under the language-policy rule, a fixed locale can be a concern when no user choice or justification is provided.
该技能文件整体以 zh-CN 语言环境呈现，且未见任何允许用户选择输出语言或说明该语言限制的自然语言声明。根据规则，若技能强制特定语言而无用户 opt-in 或正当限定，属于语言/locale 策略风险。
No suspicious patterns detected.
