save_docx
AI agents use save_docx to create or update resources in Asset Aware — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Asset Aware environment.
This tool creates or modifies files by saving content as DOCX documents. It is a reversible Write operation since saved documents can be edited, overwritten, or deleted. Severity is medium because unintended overwrites could lose data, but the effect is not irreversible (deleted files may be recoverable). Confidence is reduced to 0.85 due to missing description.
From the tool's definition Tool name 'save_docx' indicates writing/saving a document in DOCX format. No description provided, but the naming pattern on this server (convert_document, convert_docx_to_*, convert_pdf_to_docx) confirms document manipulation capabilities.
Attacks that exploit this kind of access
save_docx. It is categorised as a Write tool in the Asset Aware MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Asset Aware MCP server in PolicyLayer and add a rule for save_docx: 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 Asset Aware. Nothing to install.
save_docx 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 save_docx 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 save_docx. 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.
save_docx is provided by the Asset Aware MCP server (u9401066/asset-aware-mcp). 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 →