AI agents use browser_save_pdf to create or update resources in LocalAnt — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LocalAnt environment.
The tool creates a new file (PDF) in the workspace, which is a Write operation. The severity is medium because while PDFs can be deleted, saving arbitrary web content as files could enable data exfiltration or workspace pollution if an AI agent saves sensitive pages without authorization. The confidence is high (0.9) because the description clearly indicates file creation with no destructive or irreversible aspects.
From the tool's definition Tool name explicitly states 'save', and description indicates it 'saves' the current page as PDF into the workspace. This is a reversible file creation/write operation.
Attacks that exploit this kind of access
Save the current page as PDF into the workspace. It is categorised as a Write tool in the LocalAnt MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LocalAnt MCP server in PolicyLayer and add a rule for browser_save_pdf: 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 LocalAnt. Nothing to install.
browser_save_pdf 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 browser_save_pdf 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 browser_save_pdf. 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.
browser_save_pdf is provided by the LocalAnt MCP server (yuga-hashimoto/localant). 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 →