AI agents use lark_mark_processed to create or update resources in Feishu Enhance — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Feishu Enhance environment.
The tool modifies a message's processed status flag, which is a data state change. This is reversible (can be unmarked) and has no destructive effects or external side effects. It fits the Write category as it updates existing data without triggering external operations or removing data. Severity is low because marking a message as processed is a benign metadata update with minimal blast radius for misuse.
From the tool's definition Tool description: '将指定消息标记为已处理' (Mark specified message as processed). This operation modifies message state/metadata by marking it as processed, which is a reversible state change typical of Write operations.
Documented attack patterns abuse exactly the kind of access lark_mark_processed gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Feishu Enhance, and nothing reaches the server without passing your rules. This is the rule we recommend for lark_mark_processed:
{
"version": "1",
"default": "deny",
"tools": {
"lark_mark_processed": {
"limits": [
{
"counter": "lark_mark_processed_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}lark_mark_processed 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.
将指定消息标记为已处理. It is categorised as a Write tool in the Feishu Enhance MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Feishu Enhance MCP server in PolicyLayer and add a rule for lark_mark_processed: 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 Feishu Enhance. Nothing to install.
lark_mark_processed 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 lark_mark_processed 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 lark_mark_processed. 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.
lark_mark_processed is provided by the Feishu Enhance MCP server (jiaxinghit/feishu-enhance-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Feishu Enhance, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
24 Feishu Enhance tools catalogued and risk-classified — across an index of 43,000+ MCP servers.