Security audit
Security checks for vulnerabilities and agentic risk
This skill does what it claims: searches Baidu for configured news topics and pushes a formatted digest to Feishu, with some privacy and localization caveats users should understand.
Install only if you are comfortable sending your chosen search topics to Baidu Qianfan and sending the generated digest through Feishu. Use least-privilege Feishu app permissions, keep the app secret and Baidu key in environment variables or a protected config file, and review any cron schedule before enabling automatic daily messages.
The skill documentation describes external search and Feishu push functionality but does not clearly warn users that their configured queries and the retrieved content will be sent to third-party services. This creates a transparency and privacy risk because users may unknowingly transmit sensitive topics, internal interests, or externally sourced content to Baidu and Feishu.
The file’s natural-language description, usage comments, and runtime messages are entirely in Chinese, and there is no indication that users can select another language or that the skill is intentionally limited to a Chinese-only audience. This creates a locale policy concern because the skill imposes a specific language experience without opt-in or justification.
The file hard-codes Chinese locale and Chinese-language output, including toLocaleDateString('zh-CN'), Chinese titles, labels, and status text. This imposes a specific language/locale on all users without any opt-in or configuration path, which matches the policy-violation category for forced language or locale.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
*/
export async function getTenantToken(appId, appSecret) {
const response = await fetch("https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal", {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ app_id: appId, app_secret: appSecret })
This code sends sensitive application credentials to an external Feishu API endpoint and later transmits message content and recipient identifiers, but there is no user-facing warning, confirmation, or explanatory comment describing these outbound data transfers. For a code file, safety-relevant network operations that handle credentials or user/system data should include some form of disclosure unless clearly covered elsewhere.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
}
export async function sendMessage(token, openId, message) {
const response = await fetch("https://open.feishu.cn/open-apis/im/v1/messages?receive_id_type=open_id", {
method: "POST",
headers: {
"Authorization": `Bearer ${token}`,
The manifest states that the skill automatically collects information and pushes it to Feishu, but it does not clearly disclose that user-defined queries and collected results are sent to two external services: Baidu for retrieval and Feishu for delivery. This creates a transparency and data-handling risk, especially for automated scheduled execution where users may not realize external transmission is occurring.
The natural-language instructions throughout the file are Chinese-only, which effectively forces a specific language for users reading and configuring the skill. There is no opt-in language choice or statement that the skill is intended only for a Chinese-speaking or region-specific audience.
The natural-language strings and comments in this file are Chinese-only, including error messages surfaced by thrown exceptions. If organizational policy requires avoiding forced language without user opt-in, this is a locale/language constraint that is not documented as optional or justified.
The natural-language description is written only in Chinese ("晨间AI资讯自动收集与推送工具"), which can indicate a language-specific skill experience without any visible opt-in, alternative locale, or justification in this manifest. Under the policy rule for natural-language violations, forcing a specific language without user choice should be flagged when not clearly documented as region-specific.
The manifest's primary description is presented only in Chinese, which can impose a language constraint on users without opt-in or explanation. The policy calls for flagging language or locale restrictions unless the skill offers language choice or clearly documents a justified region-specific limitation.
The manifest requires several sensitive credentials, including API keys and an app secret, but provides no warning about secure storage, least-privilege use, or avoiding logging and hardcoding. This increases the chance that operators mishandle secrets during installation or deployment, leading to credential exposure.