Security audit
Security checks for vulnerabilities and agentic risk
This is a disclosed Chinese-language cross-border product compliance lookup skill with no code execution, credential access, persistence, or hidden data movement.
Install this as a quick reference aid, not as a substitute for legal or customs advice. Confirm the product category, destination market, and current regulations before acting, especially because the skill is primarily Chinese-language and relies on bundled compliance data that may age.
The manifest description is entirely in Chinese and the skill examples and follow-up prompt assume Chinese interaction, which can amount to forcing a specific language without user opt-in. The file does not state that language is selectable or limited for a justified region-specific reason.
The trigger list contains broad phrases such as customs holds, returns, and certification questions that can match general support, logistics, or legal-adjacent queries outside the skill’s intended scope. This can cause the skill to activate on ambiguous requests and provide jurisdiction-specific compliance guidance when the user may actually need customer support, legal advice, or case-specific customs handling, increasing the risk of misleading actions.
The instruction to auto-recognize any category name or keyword without boundary conditions makes activation and routing overly permissive. In practice this can misclassify user intent or infer regulated product categories from weak keyword matches, leading the agent to return incorrect compliance requirements for the wrong product class or market.
The prescribed clarification prompt is hard-coded in Chinese and gives no option to adapt to the user's requested language. Without documented locale justification or an opt-in mechanism, this conflicts with the policy against forcing a specific language.
This JSON response uses Chinese natural-language strings throughout, including compliance status, descriptions, actions, and warnings, with no indication that the user selected Chinese or that the skill is intentionally region- or locale-specific. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The enum values for complianceStatus are fixed to Chinese phrases, which imposes a specific language on all outputs. Under the policy, locale or language constraints should either offer user choice or be clearly justified as region-specific; this file does neither.
The document title and the entire content are presented in Chinese, and it does not indicate that users may choose another language or locale. Under the policy for natural-language violations, forcing a specific language without user opt-in is in scope even for markdown content.
The usage section presents all invocation examples exclusively in Chinese, which can imply the skill should be used in a specific language. Because the file does not state that other languages are supported or provide an opt-in language choice, this may conflict with language/locale choice expectations.
The request payload sets productCategory to a Chinese-language value (母婴) while the destination country is US, indicating a fixed language choice in configuration data. Because there is no accompanying indication of user opt-in or documented locale rationale in this file, this may violate the policy against forcing a specific language or locale.
The enum for productCategory hard-codes values in two specific languages, which imposes a locale/language constraint in natural-language data accepted by the skill. There is no indication in this file that users can choose other locales or that this restriction is justified as region-specific.
