AI agents use log_dialog to create or update resources in Prompts — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Prompts environment.
The tool appends dialogue logs and todo items to a markdown file (todos.md). This is a Write operation because it creates new records and modifies existing files, but the modifications are reversible (entries can be edited or deleted). It does not execute arbitrary code, delete data irreversibly, or perform financial operations.
From the tool's definition Tool description indicates 「記録對話日誌」(log dialog) and "append todos to todos.md" - creates/modifies the todos.md file by appending entries. This is a write operation that creates or modifies data reversibly.
Attacks that exploit this kind of access
【记录日志】记录对话日志，追加待办到 todos.md。. It is categorised as a Write tool in the Prompts MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Prompts MCP server in PolicyLayer and add a rule for log_dialog: 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 Prompts. Nothing to install.
log_dialog 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 log_dialog 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 log_dialog. 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.
log_dialog is provided by the Prompts MCP server (thana0623/pmcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →