Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language Amazon pricing advice skill with no executable code, hidden data access, or persistence.
Install this if you are comfortable using a Chinese-language Amazon seller pricing assistant and sharing the product costs, prices, sales volume, FBA fees, and competitor links needed for analysis. Verify any Amazon fee and benchmark numbers against current Amazon documentation before relying on pricing recommendations.
The skill description, commands context, and example dialogue are presented entirely in Chinese, which implies a fixed language experience. Under the policy, locale or language restrictions should either provide user opt-in/choice or be explicitly justified as region-specific; neither is present here.
The manifest description embeds multiple generic trigger phrases such as 'amazon pricing', '定价策略', and 'pricing optimization' without clear scoping to a narrow workflow. Broad triggers can cause unintended activation in unrelated conversations, which may lead the agent to collect business-sensitive pricing, cost, and sales data when the user did not explicitly intend to invoke this skill.
The manifest description and the rest of the skill content are written entirely in Chinese, while also advertising support for multiple international markets. There is no indication that users may choose another language or that Chinese-only usage is an intentional, justified regional constraint.
This markdown file is written entirely in Chinese, with no indication that the user can choose another language or that the skill is intentionally limited to a Chinese-language audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale violation.
This markdown file contains user-facing instructional content exclusively in Chinese, and there is no indication that the skill is region-specific or that users can opt into this language. Under the policy, forcing a specific language without user choice is a natural-language policy violation.
The manifest description is written entirely in Chinese, which can impose a language/locale constraint on users without offering a choice or explaining that the skill is intended only for a Chinese-speaking audience. This matches the policy concern for language or locale restrictions expressed in natural language.
No suspicious patterns detected.
