prompthub_update_repo · Prompthub MCP: Risk & Policy

WHAT IT DOES

What prompthub_update_repo does on Prompthub

AI agents use prompthub_update_repo to create or update resources in Prompthub — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Prompthub environment.

WHY IT NEEDS A POLICY

Why prompthub_update_repo needs a policy

While the primary action is replacing/updating repository content (Write), the mechanism includes automatic deletion of omitted files, which borders on destructive. However, since the deletions are secondary to the primary write operation and the user has full control by providing the complete set of files, this is classified as Write rather than Destructive.

From the tool's definition The description explicitly states 'Replace ALL content' and 'FULL REPLACE, not a partial merge — any file you omit is DELETED.' This indicates the tool modifies repository content, including deletion of omitted files as a side effect.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

prompthub_update_repo Rate-limited

prompthub_update_repo 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "prompthub_update_repo": {
      "limits": [
        {
          "counter": "prompthub_update_repo_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Prompthub, so you can run agents against it safely.

FAQ

Questions about prompthub_update_repo

What does the prompthub_update_repo tool do? +

Replace ALL content of one of YOUR repositories with the provided body. This is a FULL REPLACE, not a partial merge — any file you omit is DELETED. To change part of a repo, first call prompthub_get_repo, edit the returned fields, then send the COMPLETE set back (map the returned. It is categorised as a Write tool in the Prompthub MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on prompthub_update_repo? +

Register the Prompthub MCP server in PolicyLayer and add a rule for prompthub_update_repo: 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 Prompthub. Nothing to install.

What risk level is prompthub_update_repo? +

prompthub_update_repo is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit prompthub_update_repo? +

Yes. Add a rate_limit block to the prompthub_update_repo 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.

How do I block prompthub_update_repo completely? +

Set action: deny in the PolicyLayer policy for prompthub_update_repo. 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.

What MCP server provides prompthub_update_repo? +

prompthub_update_repo is provided by the Prompthub MCP server (lionelhao/prompthub-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.