AI agents use log_module 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's primary function is to record and persist module modifications, which is a Write operation (creates/modifies data reversibly). It does not execute code, delete data, or move money. Severity is medium because logging incorrect module metadata could mislead an AI agent about code state, but the effect is reversible and doesn't directly impact production code execution.
From the tool's definition Tool description indicates '按模块记录一次修改' (log a module modification) - this creates or records data about code changes. The description mentions calling it after modifications, suggesting it writes/persists modification records in a directory structure.
Attacks that exploit this kind of access
【模块记录】按模块记录一次修改（目录式）。修改功能前先 read_module，修改后调用此工具。. 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_module: 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_module 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_module 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_module. 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_module 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 →