AI agents invoke navigate_back to trigger actions in Selenium. 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.
While technically reversible by navigating forward, this tool executes a browser control action whose effects depend on runtime state (current browser history). It falls under Execute category as it triggers external operations via browser automation.
From the tool's definition Tool performs browser navigation action ("Go back in browser history") which is an external operation that modifies browser state and could trigger side effects like re-executing JavaScript, reloading resources, or navigating to unexpected pages depending on…
Attacks that exploit this kind of access
Go back in browser history. It is categorised as a Execute tool in the Selenium MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Selenium MCP server in PolicyLayer and add a rule for navigate_back: 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 Selenium. Nothing to install.
navigate_back is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the navigate_back 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 navigate_back. 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.
navigate_back is provided by the Selenium MCP server (scv-consultants/selenium-mcp). 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 →