Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it says: it analyzes WeChat Channels videos using a disclosed external API, with user confirmation before paid calls or video upload.
Install only if you are comfortable sending the selected video and its metadata to the 曼格云/we-media.cn analysis service and temporary upload storage. Do not use it on private, confidential, or copyrighted media unless you have permission, and keep WM_API_KEY in a local environment variable or config file rather than chat or exported reports.
该代码片段的核心职责是处理微信视频号互动数据口径：精确解析整数计数、将旧网关字段 favoriteCount/likeCount 映射到规范语义、保留 metricDetails、计算互动总量与结构占比，并输出谨慎的互动结构描述。它明确限制自己不推断收藏意图、不计算播放率、不过度解释传播原因。这与声明中的“视频拆解 + AI 深度分析 + 多格式导出”的整体技能描述存在明显不一致。虽然声明提到互动数据采集，当前代码可视为其中一个很小的支撑模块，但单看该代码，其实际行为与宣称的主要用途相差较大，因此应判定为描述与行为不匹配。
声明的核心功能是“视频号视频拆解与分析”，包括内容采集、视觉结构分析、AI 运营分析和多格式导出；而本代码块的核心功能是“API 平台通用支持/计费估算”。虽然它提到 we-media.cn / 曼格云相关接口，可能属于同一系统的基础设施组件，但该代码与声明中的主要用户可见能力没有直接对应关系。它既不接收视频链接或本地视频进行分析，也不调用任何视频拆解、元数据抓取、AI 评估或导出逻辑，因此属于明显的描述—行为不一致。
The skill explicitly instructs use of environment variables, local file reads/writes, and outbound network requests, but it does not declare any explicit permission or allowed-tools scope. That creates an overbroad execution surface where a host may grant more capability than users or reviewers can easily verify, increasing the risk of unintended data access or transmission.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
先用小样本验证；未经我同意不自动扩大采集范围、不创建定时任务。
文档入口：https://api.we-media.cn/client/ai-guide
API 市场与逐产品 AI 文档：https://api.we-media.cn/client/products
公开产品目录：GET https://api.we-media.cn/api/v1/public/products
配置 Key 后，预估使用同 Key 请求 GET https://api.we-media.cn/api/v1/products，考虑参数附加价与调用次数；不能把价格写死。
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
先用小样本验证；未经我同意不自动扩大采集范围、不创建定时任务。
文档入口：https://api.we-media.cn/client/ai-guide
API 市场与逐产品 AI 文档：https://api.we-media.cn/client/products
公开产品目录：GET https://api.we-media.cn/api/v1/public/products
配置 Key 后，预估使用同 Key 请求 GET https://api.we-media.cn/api/v1/products，考虑参数附加价与调用次数；不能把价格写死。
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
先用小样本验证；未经我同意不自动扩大采集范围、不创建定时任务。
文档入口：https://api.we-media.cn/client/ai-guide
API 市场与逐产品 AI 文档：https://api.we-media.cn/client/products
公开产品目录：GET https://api.we-media.cn/api/v1/public/products
配置 Key 后，预估使用同 Key 请求 GET https://api.we-media.cn/api/v1/products，考虑参数附加价与调用次数；不能把价格写死。
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
先用小样本验证；未经我同意不自动扩大采集范围、不创建定时任务。
文档入口：https://api.we-media.cn/client/ai-guide
API 市场与逐产品 AI 文档：https://api.we-media.cn/client/products
公开产品目录：GET https://api.we-media.cn/api/v1/public/products
配置 Key 后，预估使用同 Key 请求 GET https://api.we-media.cn/api/v1/products，考虑参数附加价与调用次数；不能把价格写死。
The documentation instructs users to upload local or decrypted video files to a public HTTPS temporary URL for downstream AI analysis, but it does not explicitly warn that this may expose private, copyrighted, or sensitive media to third-party infrastructure. Because the skill handles decrypted media and the resulting URL is described as publicly accessible, users may unknowingly disclose content beyond their local environment, increasing privacy and compliance risk.
The raised ValueError message is hard-coded in Chinese, which enforces a specific language in user-visible output. There is no indication of user opt-in, locale negotiation, or documentation justifying a Chinese-only constraint.
The snapshot function creates directories and atomically writes JSON data to the provided path, which is a file-modifying operation. While the function docstring describes replacement behavior, there is no user-facing confirmation, prompt, or visible disclosure in the executable path warning that existing snapshot content may be overwritten.
The comments at L001-L002 are written only in Chinese, which can reflect a fixed language assumption in the skill asset. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale constraint is clearly justified.