AI agents use upload_image to create or update resources in RendrKit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your RendrKit environment.
This tool creates and stores data (uploads images to a hosted service), making it a Write operation. Severity is medium because the blast radius is limited to storage/quota exhaustion and potential abuse of hosting resources, but the upload itself is reversible (images can be deleted). It does not execute arbitrary code, delete data, or move money.
From the tool's definition Tool description states 'Upload an image to get a hosted URL' — creates a new resource (hosted image) with side effects (storage allocation, URL generation). Accepts user-provided content (public URL or base64 data) and persists it.
Attacks that exploit this kind of access
Upload an image to get a hosted URL that can be used as photo_url in templates. Provide either a public URL to re-upload or base64-encoded image data. It is categorised as a Write tool in the RendrKit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the RendrKit MCP server in PolicyLayer and add a rule for upload_image: 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 RendrKit. Nothing to install.
upload_image 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 upload_image 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 upload_image. 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.
upload_image is provided by the RendrKit MCP server (vbiff/rendrkit-mcp-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 →