AI agents use html_upload to create or update resources in Llama — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Llama environment.
This tool creates or modifies data reversibly by uploading/replacing HTML content for a deal. It is a Write operation because it changes deal information without permanently deleting or destroying data, and carries medium severity due to potential for overwriting important deal documentation or introducing malicious HTML content into the platform.
From the tool's definition Tool name 'html_upload' and description 'Upload (PUT) a new HTML version for a SPECIFIC DEAL' indicate a create/modify operation via HTTP PUT method. The tool modifies deal content by uploading a new HTML version.
Attacks that exploit this kind of access
Upload (PUT) a new HTML version for a SPECIFIC DEAL. It is categorised as a Write tool in the Llama MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Llama MCP server in PolicyLayer and add a rule for html_upload: 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 Llama. Nothing to install.
html_upload 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 html_upload 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 html_upload. 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.
html_upload is provided by the Llama MCP server (llama-ventures/llama-cli). 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 →