Execute JavaScript in the current Safari tab and return the result. Powerful for reading page content, filling forms, clicking elements, or extracting data. No Accessibility permissions needed. REQUIRES: Safari Develop menu enabled, then Develop > Developer Settings > Allow JavaScript from Apple ...
AI agents invoke safari_js to trigger actions in MacWright. 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.
This tool executes arbitrary JavaScript code in a Safari browser context, which is a form of code execution. While it can be used for benign purposes like reading page content, it has the capability to perform any action that JavaScript can perform in a browser, including potentially malicious activities like stealing credentials, exfiltrating data from web pages, or hijacking user interactions.
From the tool's definition Execute JavaScript in the current Safari tab and return the result. Powerful for reading page content, filling forms, clicking elements, or extracting data.
Attacks that exploit this kind of access
Execute JavaScript in the current Safari tab and return the result. Powerful for reading page content, filling forms, clicking elements, or extracting data. No Accessibility permissions needed. REQUIRES: Safari Develop menu enabled, then Develop > Developer Settings > Allow JavaScript from Apple Events (macOS Sonoma+). If you get a permission error, use run_applescript to open Developer Settings via the Develop menu. Code can be a single expression (. It is categorised as a Execute tool in the MacWright MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MacWright MCP server in PolicyLayer and add a rule for safari_js: 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 MacWright. Nothing to install.
safari_js 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 safari_js 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 safari_js. 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.
safari_js is provided by the MacWright MCP server (ruchit-p/macwright). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
safari_js is one line of MacWright's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →