Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Kuaishou public-data retrieval tool that uses a third-party API token and saves result logs locally, with no evidence of hidden execution, private-data access, or destructive behavior.
Before installing, confirm you are comfortable sending Kuaishou keywords, URLs, limits, and your GUAIKEI_API_TOKEN-backed requests to guaikei.com. Treat saved logs as retained collected data, especially if comments or account-analysis outputs are sensitive for your organization, and delete or protect them according to your retention policy.
The documented purpose is much broader than the visible implementation, suggesting overclaiming or incomplete disclosure. Even if not overtly malicious, that is security-relevant because defenders cannot accurately assess data access, network use, or side effects, and users may expose credentials or sensitive business queries to an insufficiently vetted integration.
The documented purpose is much broader than the visible implementation, suggesting overclaiming or incomplete disclosure. Even if not overtly malicious, that is security-relevant because defenders cannot accurately assess data access, network use, or side effects, and users may expose credentials or sensitive business queries to an insufficiently vetted integration.
The documented purpose is much broader than the visible implementation, suggesting overclaiming or incomplete disclosure. Even if not overtly malicious, that is security-relevant because defenders cannot accurately assess data access, network use, or side effects, and users may expose credentials or sensitive business queries to an insufficiently vetted integration.
The documented purpose is much broader than the visible implementation, suggesting overclaiming or incomplete disclosure. Even if not overtly malicious, that is security-relevant because defenders cannot accurately assess data access, network use, or side effects, and users may expose credentials or sensitive business queries to an insufficiently vetted integration.
Without declared permissions the skill's intent is opaque and cannot be validated.
The file consistently mandates Chinese-language interaction and documentation, but does not state that language selection is optional or user-driven. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The description contains broad trigger phrases such as account teardown, competitor analysis, replication, scraping, and diagnosis that can match many ordinary user requests outside a tightly bounded skill scope. In an agent-routing context, this can cause over-invocation of a data-scraping skill, leading to unintended collection or analysis of third-party platform data and increasing the chance of privacy, policy, or misuse issues.
The README states that all task results are automatically saved under logs/, but it does not warn users that scraped public data, including comment text and account analysis outputs, will be persisted to disk. This creates a real data-handling risk because operators may unknowingly retain potentially sensitive or regulated content, increasing exposure through local compromise, backups, or unintended sharing.
The script reads a credential from GUAIKEI_API_TOKEN and then sends requests through comment.createCommentTask and comment.getCommentTask using the token, URL, and limit. Although this network behavior is central to fetching comments, this file does not explicitly warn the user that their input and credential-backed request will be sent to an external service.
The code persists the full command output, including the requested URL and retrieved comments, to a timestamped local file via log.taskWrite. While the script logs progress messages, there is no explicit disclosure here that execution will create a file containing collected data, which is a safety-relevant file write operation.
Multiple error messages returned by this utility are fixed Chinese strings such as '请求失败', '响应解析失败', and 'token 必须是非空字符串'. This creates a locale-specific user experience without offering any language choice or documenting a justified regional constraint.
This file contains user-facing warning and info strings only in Chinese ("警告: 你的 GUAIKEI_API_TOKEN 未正确配置" and "已使用配置的私有TOKEN"). Per the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified, which is not present here.
The manifest description is entirely in Chinese and presents the skill behavior and trigger conditions only in that language. That can violate language/locale policy when no user opt-in or documented region-specific justification is provided.
Natural-language policy violations include forcing a specific language without user opt-in. The README content is fully Chinese and does not indicate any multilingual support, fallback, or explicit justification for a Chinese-only experience.
The file title and content are entirely in Chinese, and there is no indication that the skill is intended only for Chinese-speaking users or that users can opt into this language. This can violate a language/locale policy when a skill implicitly forces one language without user choice or justification.
This markdown file presents all instructions, parameter descriptions, and examples only in Chinese. Under the policy rules, forcing a specific language without offering a language or locale choice can be a natural-language policy violation when no justification or opt-in is provided.
This code presents descriptions, examples, and runtime messages entirely in Chinese, which imposes a specific language on users. The file does not offer a language/locale option or indicate that the skill is intentionally limited to a Chinese-only regional context.
The manifest frames the skill as a Kuaishou account analysis/fetching tool and lists three data-retrieval capabilities, but does not mention credential handling. Reading process.env.GUAIKEI_API_TOKEN introduces secret access behavior that is not user-visible and is not justified by the stated purpose alone.
The manifest describes capabilities around searching videos, fetching public works, and analyzing comments, which are primarily read/analysis operations. This CLI additionally persists the full output to a local JSON file via log.taskWrite, a behavior not mentioned in the description and not obviously required to fulfill the stated user-facing purpose.
This code presents user-facing natural-language strings entirely in Chinese, including errors and help output. That creates a locale/language policy concern because the skill does not offer any language selection or opt-in for users who may expect another language.
The code's user-facing messages are hardcoded in Chinese, including error and success output. This imposes a specific language without opt-in or any documented justification, which matches the natural-language locale policy violation category.
The file defines POST and GET helpers that send request data and a TOKEN header to a remote host via HTTPS. There is no confirmation prompt, user-facing log, or warning in this code indicating that user-supplied data and credentials will be transmitted over the network.
The thrown error string 重试${maxAttempts}次后失败 is fixed in Chinese, which imposes a specific language in a user-visible message. The file does not offer any locale choice or indicate that the skill is intentionally limited to Chinese-language usage.
The call to new Date().toLocaleString() produces locale-dependent output and implicitly forces whichever language/locale the runtime environment uses. Under the policy, locale-sensitive behavior should either offer user choice or be clearly documented when constrained.
This code emits multiple natural-language error messages only in Chinese, such as at L05, L10, L14, L18, and L23. The policy specifically calls for flagging language or locale constraints when a skill forces a specific language without user opt-in, and this file provides no alternative locale handling.
No suspicious patterns detected.
