unprotect_document
Remove password protection from a Word document.
This record as markdown: /tools/cowork-bench/unprotect-document.md
What unprotect_document does on Cowork Bench
AI agents use unprotect_document to create or update resources in Cowork Bench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cowork Bench environment.
Why unprotect_document is rated Medium
This tool modifies a document's security settings by removing its password protection. It's a Write operation (reversible in theory — protection can be re-added), but carries high severity because it bypasses access controls, potentially exposing sensitive content and undermining document confidentiality.
From the tool's definition Remove password protection from a Word document
Attacks that exploit this kind of access
The rule that runs unprotect_document safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For unprotect_document, this is the rule to start with:
unprotect_document 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Cowork Bench, apply this rule, and every unprotect_document call is checked against it from then on.
Questions about unprotect_document
Remove password protection from a Word document. It is categorised as a Write tool in the Cowork Bench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cowork Bench MCP server in PolicyLayer and add a rule for unprotect_document: 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 Cowork Bench. Nothing to install.
unprotect_document 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 unprotect_document 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 unprotect_document. 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.
unprotect_document is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
This server
Across the catalogue