Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Kuaishou public-data collection tool that uses a third-party API token and saves results locally, with no evidence of hidden execution, destructive behavior, or credential theft.
Install only if you intend to use Guaikei's API for Kuaishou public-data analysis. Treat submitted keywords, profile/video URLs, and returned comments/posts as data shared with the API provider, and periodically delete or protect the local logs directory if the collected data is sensitive business research.
The manifest description is primarily written in Chinese and includes trigger phrases only in Chinese for invocation guidance. This can create a de facto language preference without stating that users may interact in another language or choose their locale, which conflicts with the policy against forcing a specific language without opt-in.
The package description and keywords are entirely in Chinese, which imposes a specific language on users without any opt-in, alternative locale, or documented region-specific justification. The policy requires either offering a language/locale choice or clearly documenting why the locale restriction is necessary.
The README states that all task results are automatically saved to a local logs/ directory, but it does not clearly warn users that search keywords, monitored profile URLs, comment data, and other scraped outputs may persist on disk. In a data-collection tool, silent persistence increases the risk of unintended disclosure, retention of sensitive business intelligence, or leakage through backups, shared workstations, and source-control mistakes.
The command descriptions, examples, and other user-facing strings are presented only in Chinese, and the file provides no mechanism for language selection or user opt-in. Under the stated policy, forcing a specific language without choice is a natural-language policy violation unless clearly justified and documented.
The script persists the fetched comment data and request metadata to disk via log.taskWrite, which is a file-write operation affecting user/system data. While the script logs progress messages, there is no user-facing disclosure here that results will be saved locally, nor an inline comment/docstring warning about this persistence behavior.
No manifest is available, so there is no stated purpose that justifies credential access or outbound API-backed task execution. This file reads GUAIKEI_API_TOKEN from the environment and uses it to create and fetch a remote 'post' task, which is a nontrivial capability beyond simple local argument processing.
The tool writes fetched results to a local JSON file automatically without clear user-facing notice or opt-in. If the fetched post data contains personal, copyrighted, or otherwise sensitive content, this silent persistence can create privacy, retention, and local disclosure risks, especially on shared systems or in automated environments.
No manifest is available, so the skill has no declared purpose or scope to justify sensitive credential access. This file explicitly reads GUAIKEI_API_TOKEN from process environment, which is a capability beyond simple local argument parsing/output formatting and therefore context-inappropriate under an unknown-purpose skill.
The code creates and retrieves a search task through imported API methods, indicating outbound authenticated service interaction. Because no manifest is available, there is no stated purpose establishing that networked remote search is intended, so this capability is unjustified in context.
Writing search results to local storage without explicit notice can expose potentially sensitive queries and returned content to other local users, backups, log collectors, or CI artifacts. The risk is elevated because persistence happens silently after a successful search, so users may not realize data has been retained.
This JavaScript file contains natural-language strings for errors, warnings, and help output entirely in Chinese, such as parameter validation errors and usage text. Because the skill does not offer user opt-in for language selection or state that it is intentionally limited to a Chinese-speaking context, it conflicts with the policy against forcing a specific language without user choice.
Several error strings are hard-coded in Chinese, including parse, timeout, network, and authentication failure messages. That imposes a specific language on users without offering a language choice or documenting a justified locale restriction.
This code constructs outbound HTTPS requests that include serialized parameters in the URL and a TOKEN header, which may transmit user or system data to an external service. Within this file there is no confirmation prompt, logging, comment, or docstring disclosing that data is being sent off-host.
The GET helper appends params to the request URL and includes a TOKEN header, causing data to be sent to an external endpoint. This file provides no user-visible warning, confirmation, or explanatory comment about that network transmission.
The user-facing warning and info messages are written only in Chinese ("警告..." and "已使用配置的私有TOKEN") with no indication of language selection or opt-in. This can violate a language/locale policy when a skill imposes a specific language on users without offering a choice or documenting a justified locale restriction.
This code emits all validation feedback in Chinese string literals, which effectively forces a specific language on users. The file does not indicate that the skill is region-specific or provide any opt-in or fallback for other locales, which matches the language/locale policy violation criteria.
The natural-language instructions and user-facing documentation are entirely in Chinese, which can amount to a forced language choice if the organization expects language/locale neutrality unless users opt in. The file does not offer an alternative language, note that the skill is intended only for Chinese-speaking users, or provide any user choice.
The file title is entirely in Chinese and provides no indication that users can choose another language or locale. Under the policy for natural-language violations, forcing a specific language without opt-in can be a concern when no justification or alternative is documented.
This markdown file contains user-facing instructions exclusively in Chinese, including headings, parameter descriptions, and examples. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.
The function sends a user-provided URL and a token to a remote API via postJson, which is a data-transmitting network operation covered by the warning requirement for code files. While retry errors are logged, there is no confirmation prompt, user-facing notice about transmitting the URL/token, or explanatory comment/docstring in this file.
This function performs a remote GET request using the provided URL and token, which transmits user or system data over the network. The file includes retry error logging, but no user-facing disclosure or explanatory documentation about this network access and data transmission.
This code performs an HTTP POST that transmits a user-provided URL along with an authentication token, but the file contains no confirmation prompt, user-facing notice, or explanatory comment/docstring disclosing that data is being sent to an external API. Under the code-file criteria, network calls that transmit user or system data should have some visible disclosure unless clearly documented elsewhere or obviously inherent to the skill's stated purpose, which is not established in this file alone.
This function makes an HTTP GET request containing the supplied URL and token, but there is no confirmation prompt, disclosure message, or explanatory comment/docstring indicating that this information will be transmitted to a remote service. Because code-file checks include network calls that transmit user or system data, the absence of any visible warning is a quality/safety gap in this file.
This code sends the user-provided keyword and related search parameters to a remote API via postJson, along with a token, but the file contains no comment, docstring, or user-facing notice describing that transmission. Under the code-file warning criteria, network calls that transmit user or system data should have some visible disclosure unless already clearly documented elsewhere or inherent to the skill's stated purpose.
The getJson call queries a remote endpoint with search parameters and an authentication token, but this file provides no comment, docstring, or user-visible disclosure that the operation sends data off-box. Although retry errors are logged, those messages do not warn users about the underlying network/data-transmission behavior.
