vlm_test_prompt · Albumentations MCP: Risk & Policy

WHAT IT DOES

What vlm_test_prompt does on Albumentations

AI agents invoke vlm_test_prompt to trigger actions in Albumentations. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why vlm_test_prompt needs a policy

This tool executes an image generation pipeline from a text prompt, triggering external processing (likely via a VLM/diffusion model). It does not merely read existing data nor write user-provided data — it runs an external operation whose output depends on the prompt argument. Severity is medium as misuse could generate inappropriate content or consume compute resources, but blast radius is limited.

From the tool's definition "Generate a preview image from a text prompt" — triggers external image generation operations based on input arguments

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

vlm_test_prompt Rate-limited

vlm_test_prompt stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "vlm_test_prompt": {
      "limits": [
        {
          "counter": "vlm_test_prompt_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about vlm_test_prompt

What does the vlm_test_prompt tool do? +

Generate a preview image from a text prompt (no input image). It is categorised as a Execute tool in the Albumentations MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on vlm_test_prompt? +

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

What risk level is vlm_test_prompt? +

vlm_test_prompt is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit vlm_test_prompt? +

Yes. Add a rate_limit block to the vlm_test_prompt 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 vlm_test_prompt completely? +

Set action: deny in the PolicyLayer policy for vlm_test_prompt. 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 vlm_test_prompt? +

vlm_test_prompt is provided by the Albumentations MCP server (ramsi-k/albumentations-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.