Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward client-side JSON query tool with some privacy-disclosure and localization caveats, but no evidence of hidden execution, persistence, or data exfiltration.
Install only if you are comfortable with a Chinese-language JSON query tool. For sensitive JSON, prefer using the reviewed static file locally or a no-ads self-hosted deployment, because enabling third-party ads or relying on a hosted copy changes the privacy posture.
This markdown file contains user-facing operational instructions exclusively in Chinese, including headings, warnings, and deployment steps. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly documented and justified.
The README makes a strong privacy/security claim that the tool is 'pure frontend' and that data is not uploaded to servers, but the same document instructs users to deploy it on hosted platforms and add third-party ad scripts. While hosting alone does not necessarily transmit JSON input to the author's server, third-party scripts can create network requests and materially change the privacy posture, making the claim misleading and potentially unsafe for sensitive data use.
The README assures users that data is not uploaded to servers, yet it documents loading Google AdSense or Baidu ad code, which necessarily causes browser requests to third parties. Even if the app logic does not intentionally submit JSON contents, these integrations undermine the blanket privacy claim and can expose metadata, tracking identifiers, referrers, and potentially sensitive context without any user-facing warning.
The invocation guidance says to directly call the skill whenever a user requests JSON querying, path extraction, or data filtering, which is broad enough to capture many ordinary requests that may be better handled natively or may involve sensitive data. Over-broad auto-invocation can cause unnecessary routing to an external tool and expand data exposure or create user-confusion about when the tool is actually needed.
The document declares lang="zh-CN" and all visible title/description text is Chinese-only, which imposes a specific language/locale on users. The file does not indicate that this is a region-specific tool or provide any user-selectable language option, so it appears to violate the language/locale choice policy.
The skill description and operational instructions are entirely in Chinese, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking audience. This can violate language/locale policy when no opt-in or justification is provided.
The natural-language instructions and examples are entirely in Chinese, and the file does not indicate that users may choose another language. Under the policy, forcing a specific language without user opt-in can be a locale/language policy issue unless the constraint is explicitly documented and justified.
The function name and toast message indicate it loads example data for the user, but after setting the sample into the textarea at L912 it calls clearAll() at L914, which wipes the JSON input and query fields. This is an active contradiction between the code's apparent documented intent and what it actually does at runtime.
