Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed Douyin public-data CLI integration that sends user-provided queries or links to a third-party API and locally saves some results for later analysis.
Install only if you are comfortable using the GUAIKEI third-party API for Douyin public-data lookups. Keep GUAIKEI_API_TOKEN private, avoid submitting sensitive research terms or links if that egress is not allowed in your environment, and periodically clean the local logs directory if saved result JSON files should not persist.
声明描述的是一个面向抖音公开数据的洞察与分析技能，核心能力应围绕抖音内容搜索、热榜获取、博主作品抓取和评论分析展开。但提供的代码片段仅是一个独立的通用 CLI 参数解析与帮助文本生成模块，不包含任何网络请求、抖音接口调用、数据抓取、数据分析、用户画像或产品机会分析逻辑。虽然此类参数解析代码可能作为更大系统的辅助组件存在，但就该代码片段本身而言，其实际行为与声明的主要功能明显不一致，因此应判定为描述与行为不匹配。
声明描述的是一个面向抖音公开数据分析的复杂技能，核心能力应涉及网络数据获取、筛选、分析与洞察输出。而提供的代码片段只是一个辅助函数：通过 fs 读取本地 package.json，解析并缓存 name 字段后返回。该行为与声明的主要目的和四项能力均不一致。虽然这可能只是整体技能中的一个辅助模块，但就此代码片段本身来看，它并未体现声明中的任何核心功能，因此存在明显不匹配。
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
## 1.0.2 - 2026-03-24
- 在SKILL.md中添加了openclaw元数据、使用帮助、许可证、标签和示例，以实现更好的集成与文档化。
- 移除了两个本地文件（.env 和 scripts/last-search.json），以优化代码结构并提升安全性。
- 文档现已更加简洁且以用户为中心，重点在于提供清晰的使用说明和数据字段解释。
- 突出技能特性、合规要点及技术流程。
Without declared permissions the skill's intent is opaque and cannot be validated.
The manifest description is entirely in Chinese, which implies a fixed language/locale expectation without offering user choice or documenting a justified region-specific constraint. The policy requires language or locale constraints to be optional or clearly justified.
The function sends the supplied Douyin video URL and token to an external API via requestApi, but this file provides no confirmation prompt, user-facing disclosure, or warning about that transmission. Because URLs and tokens can reveal user activity or access credentials, this is a safety-relevant outbound data transfer.
This function performs a GET request that includes the video URL, limit, and token, but the file contains no prompt, print/log notice, or explicit warning that user-supplied data is being sent to a remote service. That omission matters because the operation transmits potentially sensitive usage data off the local system.
The CLI persists fetched comment results to a local JSON file after already printing them to stdout, with no indication in the help text or runtime messaging that data will be stored on disk. This creates an unnecessary data retention surface: comment content may include personal data or sensitive business research inputs, and silent persistence increases the risk of unintended disclosure on shared hosts or developer machines.
The tool writes fetched comment data to disk without a user-facing warning, confirmation, or explicit export request. Even if the source data is public, silent storage can violate user expectations, create compliance/privacy issues, and leave durable artifacts containing scraped content and analysis inputs on the local system.
The manifest describes analysis of Douyin public data via search, hot list, creator posts, and comments. In this file, the skill additionally reads a local environment variable (GUAIKEI_API_TOKEN) to obtain credentials, which introduces secret-handling capability not disclosed in the stated purpose and is not obvious from a public-data insight skill description.
The code initiates remote API operations to create and retrieve a post task without presenting a clear disclosure that user-supplied URLs and request parameters will be sent to an external service. In combination with later local file logging, this can violate user expectations and create privacy/compliance issues, especially in environments where data egress must be explicit.
The CLI persists the full fetched results to a local JSON file without any explicit user consent, retention policy, or minimization. Even though the source data is described as public, the saved output may still contain aggregated profile/content data that users do not expect to be stored locally, creating privacy and local data exposure risk on shared systems.
User-visible descriptions, help output, errors, and status messages are presented only in Chinese, effectively forcing a specific language on all users. The file does not offer any language selection, fallback, or documented locale constraint that would justify this restriction.
The CLI persists full search output to a local JSON file, including user-supplied keywords and returned results, without any explicit notice or consent mechanism. In this skill context, searches may reveal business research targets, marketing plans, or sensitive investigative interests, and storing them on disk increases the risk of unintended disclosure through shared machines, backups, or log collection.
The code emits all user-facing status and error messages in Chinese, such as the validation errors on these lines. For a general utility file, this imposes a specific language on users without opt-in or justification, which matches the language/locale policy violation criteria.
The schema's title and description are written entirely in Chinese, which imposes a specific language/locale in user-facing metadata. For a general-purpose schema file, this can violate language/locale policy when no opt-in, fallback, or justification for the language restriction is provided.
This JSON schema includes natural-language title and description strings only in Chinese, which imposes a specific language on downstream users or tooling without any visible opt-in or justification in the file. Under the policy, forcing a specific language without user choice can be a locale-policy violation.
This JSON schema contains user-facing natural-language fields such as title and description entirely in Chinese. Under the policy, forcing a specific language without user opt-in or a documented locale-specific justification is a natural-language policy concern.
The title and descriptions are written only in Chinese, which constitutes a language/locale constraint in the natural-language content of the file. There is no indication that the skill is region-specific or that users can opt into this language, so it may violate the language-choice policy.
This JSON schema contains natural-language titles and descriptions exclusively in Chinese, which can impose a specific language on users or downstream tooling without documenting a locale-specific scope. Under the policy, forcing a specific language without opt-in can be a language/locale policy violation.
The title and description are written only in Chinese, which can impose a language choice on users or downstream tools consuming this schema. The file does not indicate that the skill is region-specific or that users may choose another language, so this appears to violate the language/locale policy criterion.
This JSON schema includes title and description fields entirely in Chinese, such as the title at L004 and repeated Chinese descriptions throughout the file. Because the file provides no indication that the skill is region-specific or that users can opt into this locale, it may violate the language/locale policy for natural-language content.
This manifest description describes many broad use cases and capabilities, but it does not define specific activation phrases, scope limits, or exclusion conditions. In manifest files, vague or overly expansive descriptions can contribute to unintended invocation because the skill appears applicable to many generic market-analysis requests.
This markdown file presents all user-facing instructions, warnings, and usage details exclusively in Chinese. Under the policy rule for language or locale constraints, forcing a single language without user choice can be a natural-language policy violation unless clearly justified or optional.
The entire file is written in Chinese and does not indicate that the skill supports other languages or that Chinese is a required locale for a region-specific use case. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy concern.
Detected: suspicious.exposed_secret_literal