High-risk tools in Chrome DevTools
15 of the 29 tools in Chrome DevTools are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
clickExecute 4/5Click on a page element
-
dragExecute 4/5Drag an element on the page
-
emulateExecute 3/5Simulate different devices and network conditions
-
evaluate_scriptExecute 5/5Execute arbitrary JavaScript on the page
-
fillExecute 4/5Input text into a form field
-
fill_formExecute 5/5Complete an entire form with values
-
handle_dialogExecute 4/5Accept or dismiss browser dialogs
-
hoverExecute 3/5Trigger hover state on an element
-
lighthouse_auditExecute 3/5Run Lighthouse audit checks on the page
-
navigate_pageExecute 5/5Navigate to a URL in the browser
-
new_pageExecute 4/5Open a new browser page
-
performance_start_traceExecute 3/5Start recording a performance trace
-
press_keyExecute 4/5Simulate keyboard input on the page
-
type_textExecute 4/5Enter text character-by-character
-
upload_fileExecute 5/5Upload a file through a form input
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.
More on Chrome DevTools
Enforce policy on Chrome DevTools
One command generates a policy scaffold for every server in your MCP config.
npx -y @policylayer/intercept init