飞书@机器人

AdvisoryAudited by Static analysis on Apr 30, 2026.

Overview

No suspicious patterns detected.

Findings (0)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

If used with the wrong chat, bot ID, or text, it could send an unintended message to a Feishu group.

Why it was flagged

The skill documents sending a Feishu group message that mentions a bot. This is expected for the skill, but it can post visible messages and notify other participants or bots.

Skill content
message action=send channel=feishu target=chat:CHAT_ID message="<at user_id=\"ou_xxx\">机器人名</at> 你好!"
Recommendation

Confirm the target chat ID, bot open_id, and message content before sending, especially in shared or production workspaces.

What this means

Anyone with the app secret or tenant token may be able to act within the Feishu app's granted permissions.

Why it was flagged

The workflow uses Feishu app credentials to obtain a tenant access token. This is purpose-aligned for Feishu API use, but the credential can authorize message-related actions.

Skill content
TOKEN=$(curl -s -X POST "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal" ... -d '{"app_id":"YOUR_APP_ID","app_secret":"YOUR_APP_SECRET"}' | jq -r '.tenant_access_token')
Recommendation

Use least-privilege Feishu app permissions, keep app secrets out of chat logs and files, and rotate credentials if they are exposed.

What this means

Messages sent through this skill may trigger other bots or workflows, so sensitive or ambiguous prompts could propagate beyond the current agent.

Why it was flagged

The skill is explicitly designed to communicate with other bots through Feishu group messages. This is disclosed and purpose-aligned, but it creates an inter-bot communication channel.

Skill content
在飞书群聊中 @其他机器人并发送消息,让被艾特的机器人收到通知并响应。
Recommendation

Only send clear, intentional messages to known bots, and avoid including secrets or private data unless the receiving bot is trusted and authorized.

What this means

A wrong or outdated stored open_id could cause future messages to target the wrong bot.

Why it was flagged

The skill recommends persisting bot open_ids for reuse. This is limited and purpose-aligned, but stored identifiers can become stale or be reused in later tasks.

Skill content
缓存机器人 open_id:获取后建议保存到 TOOLS.md 或数据库,避免重复查询
Recommendation

Store only the needed bot identifiers, label them clearly, and periodically verify them against trusted Feishu message history or admin records.