AI agents use feishu_send_message to create or update resources in autoMate — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your autoMate environment.
Sending a message is a Write operation—it creates new data (the message) that persists in the system and affects other users who receive it. While not destructive or financial, misuse could result in spam, misinformation, or communication of sensitive information to unintended recipients. Severity is medium due to moderate blast radius (social/communication impact) and the reversibility of deletion.
From the tool's definition Tool name 'feishu_send_message' indicates it sends messages to Feishu (ByteDance's collaboration platform). The verb 'send' indicates a write operation that creates/modifies data (a new message). Description is empty, limiting direct confirmation.
Documented attack patterns abuse exactly the kind of access feishu_send_message gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and autoMate, and nothing reaches the server without passing your rules. This is the rule we recommend for feishu_send_message:
{
"version": "1",
"default": "deny",
"tools": {
"feishu_send_message": {
"limits": [
{
"counter": "feishu_send_message_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}feishu_send_message stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
feishu_send_message. It is categorised as a Write tool in the autoMate MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the autoMate MCP server in PolicyLayer and add a rule for feishu_send_message: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches autoMate. Nothing to install.
feishu_send_message is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the feishu_send_message rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for feishu_send_message. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
feishu_send_message is provided by the autoMate MCP server (yuruotong1/automate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 128 autoMate tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
128 autoMate tools catalogued and risk-classified — across an index of 42,500+ MCP servers.