leakstop

What the scan recorded

Anthropic directory

Listed as leakstop@anthropic-plugin-directory

Observed events

every prompt, Edit|Write|NotebookEdit calls, Bash calls, Read calls, WebFetch|WebSearch|Agent|SendMessage|SendFile|Artifact|ArtifactData|ArtifactComments|PushNotification|SendFeedback|RemoteTrigger calls, /"^mcp__"/ calls, Bash|Read calls

Hooks

session.start, prompt.submit, command.run {command=leakstop}, ui.render {component=AbovePrompt}, ui.render {component=Pane, requestId=leakstop}, tool.call {tool=Edit|Write|NotebookEdit}, tool.call {tool=Bash}, tool.call {tool=Read}, tool.call {tool=WebFetch|WebSearch|Agent|SendMessage|SendFile|Artifact|ArtifactData|ArtifactComments|PushNotification|SendFeedback|RemoteTrigger}, tool.call {tool=/"^mcp__"/}, tool.call {tool=Bash|Read}, tool.call {tool=/"^mcp__"/}

API calls

$.clock.now, $.command.register, $.fs.exists, $.fs.read, $.fs.stat, $.fs.write, $.process.run, $.session.cwd, $.session.surfaces, $.state.get, $.state.set, $.store.delete, $.store.get, $.store.set, $.ui.ask, $.ui.close, $.ui.log, $.ui.open, $.ui.resolve, $.ui.status

Validation on 2.1.302

Passed

Scanned revision

a273213c82be

Marketplace passed

leakstop

UI rewrite review

UI hook source contains control-character strings. Review any values passed to next() as rewritten props.text; the scanner does not trace whether these strings reach that call. leakstop/hooks/leakstop.tsx:317, leakstop/hooks/leakstop.tsx:439

These are the hooks and API calls reported by claude plugin validate. Access levels describe the widest reach of those calls and are not safety ratings. Validation is a static check, not a runtime test, and a passing result does not prove that a mod works or is safe. How the scan works.