Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Kuaishou public-data extraction tool that uses a third-party API token and saves results locally, with privacy and retention cautions for users.
Install only if you are comfortable sending Kuaishou keywords, profile/video URLs, and request parameters to guaikei.com using your GUAIKEI_API_TOKEN. Treat fetched comments and creator metadata as potentially personal data, review platform/legal obligations, and delete or secure the local logs directory if results should not persist.
The skill instructions, trigger guidance, routing rules, and user-facing interaction expectations are written to operate in Chinese, and the examples direct the agent to ask follow-up questions and report results in that language style. There is no opt-in or alternative language guidance for users who may prefer another locale, which can violate a language/locale choice policy.
The README explicitly states that all task results are automatically saved to a local logs/ directory, but it does not warn users that scraped platform data, URLs, comments, and analysis outputs may persist on disk beyond the session. In a data-extraction tool, this increases the risk of unintended retention, local disclosure, and secondary sharing of collected data, especially on shared systems or in environments with weak filesystem hygiene.
The documentation describes bulk extraction of Kuaishou search results, creator posts, and comments up to 10,000 records, but provides no warning that this can collect privacy-sensitive content, identifiers, and metadata at scale. In this context, the omission increases the risk of misuse, non-compliant data handling, and unsafe operator assumptions that the tool is appropriate for unrestricted collection.
The script persists fetched comment data to a local JSON file after successful execution, creating a copy of externally sourced data without any consent prompt, retention control, or visibility into where and how long it is stored. If comments contain personal data or sensitive content, this can expand data exposure through unintended local retention, especially on shared systems or agent runners.
The script writes full comment results to disk without an explicit user warning in the command flow, which can surprise users who expect a read-only fetch operation. Silent persistence increases privacy and operational risk because retrieved content may remain on disk beyond the session and be accessible to other local users, backup systems, or later processes.
The script reads GUAIKEI_API_TOKEN from the environment and sends requests using the user-provided profile URL to create and fetch a remote task. While success messages are printed after the request starts, there is no clear upfront warning or comment that the input URL and token-backed request will be transmitted to an external service.
The script writes the full fetched results to a local JSON file using a filename derived from user-controlled input after normalization. This creates a privacy and data-handling risk because potentially sensitive scraped content is persisted on disk without clear consent, retention controls, or visible warning in this file, increasing exposure if the host is shared or logs are collected.
The CLI writes the full search output, including user-provided keywords and returned results, to a local file automatically without an explicit runtime warning or opt-in. This can create unintended local data persistence, exposing potentially sensitive search activity or scraped content to other local users, backups, or later collection by unrelated processes.
This code sends request data over the network and includes a TOKEN header, which falls under network transmission of user or system data and access to credentials. The file contains no confirmation prompt, user-facing logging, or explanatory comments/docstrings warning about this behavior.
This JavaScript file contains multiple user-facing error strings in Chinese, such as the validation messages printed via utils.printError. Because the skill forces a specific language in its natural-language output without any opt-in or documented regional limitation, it presents a language/locale policy concern.
The file's headings, parameter descriptions, and usage guidance are entirely in Chinese, which effectively forces a specific language for users reading the skill documentation. Under the policy, language constraints should either be optional/opt-in or explicitly documented and justified as region-specific.
The CLI descriptions and examples shown to users are entirely in Chinese, and the rest of the script's user-facing output follows the same pattern. Forcing a specific language without opt-in can violate language/locale policy when the tool may be used in broader contexts.
With no manifest available, the skill's intended scope is unknown, so accessing process environment for credentials is an extra capability not justified by any stated purpose. The code explicitly derives a token from GUAIKEI_API_TOKEN before making the comment task request.
The script's descriptions, help text, and runtime messages are entirely in Chinese, with no option to select another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation unless explicitly justified.
The command descriptions, examples, warnings, and runtime messages are presented in Chinese, with no indication that another language can be selected. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified.
This JavaScript file contains natural-language comments, error messages, and help text exclusively in Chinese, including thrown errors and CLI help output. Because the file does not offer a language choice or document a justified locale restriction, it creates a language/locale policy concern under the stated rule.
The code emits user-facing status and error messages only in Chinese, such as the validation errors on these lines. This can violate a language/locale policy when the skill does not offer user opt-in or document that it is intended only for Chinese-speaking users.
Several user-visible error strings are written only in Chinese, including the authentication failure message. This enforces a specific language without any visible opt-in or locale selection, which matches the language/locale policy violation category.
This code file contains a natural-language string literal that forces a specific language (重试${maxAttempts}次后失败) for user-visible error output. The file does not indicate any user opt-in, language selection mechanism, or justified locale restriction, which conflicts with the policy against forcing a specific language without choice.
The module comment and banner text indicate the skill presents user-facing content in Chinese, and the logging uses locale-dependent formatting without any visible user opt-in or language selection. This can violate language/locale policy when a skill forces a specific language for all users.
The printed banner contains fixed Chinese text shown to users every time the banner is displayed. Because no alternative language or opt-in mechanism is present in this file, the skill appears to enforce a specific language for user-visible output.
