adversary

What the scan recorded

Observed events

ExitPlanMode calls, every prompt, Read|Grep|Glob calls, every tool call

Hooks

tool.call {tool=ExitPlanMode}, prompt.submit, ui.render {component=AbovePrompt}, session.start, agent.offer {agent=adversary:reviewer}, command.run {command=adversary}, tool.call {tool=Read|Grep|Glob}, tool.call, prompt.submit {origin has {kind=task-notification}, prompt.attachment {type=queued_command}, turn.complete, ui.render {component=Pane, requestId=adversary}, ui.close {id=adversary}, session.end

API calls

$.agent.list, $.agent.register, $.agent.spawn, $.clock.now, $.command.register, $.env.get, $.fs.exists, $.fs.list, $.fs.read, $.fs.stat, $.fs.write, $.mcp.call, $.mcp.connect, $.process.run, $.prompt.fill, $.session.id, $.session.root, $.state.get, $.state.set, $.tool.call, $.tool.list, $.ui.close, $.ui.log, $.ui.open, $.ui.resolve, $.ui.toast

Validation on 2.1.304

Passed

Scanned revision

1e9bcd801134

Marketplace passed

bobtat-plugins

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. plugins/adversary/hooks/artifact.ts:29, plugins/adversary/hooks/guard.ts:25, plugins/adversary/hooks/triage.tsx:69

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. What a mod can access and how the scan works.