AI agents use pitch_upload_file 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.
Uploading files creates new data or modifies existing pitch records on the platform. This is a Write operation (reversible via deletion) rather than Read (passive retrieval) or Destructive (irreversible). Severity is medium because file uploads could introduce malicious content or clutter if misused by an agent, but impact is limited to a single pitch and can be undone.
From the tool's definition Tool name 'pitch_upload_file' and description 'Attach a file... to the' indicate file creation/modification action on the Llama Ventures platform. The description is incomplete (cuts off mid-sentence), but the intent to attach/upload files is clear.
Attacks that exploit this kind of access
Attach a file (deck, one-pager, deck PDF, screenshot, etc.) to the. 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 pitch_upload_file: 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.
pitch_upload_file 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 pitch_upload_file 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 pitch_upload_file. 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.
pitch_upload_file 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 →