How content that reaches your agents from outside is scanned, what an agent sees when something is flagged, how you choose between withholding and delivering it, and how you review what was flagged. What the scan is and how well it scores is on Controls.
Everything an agent with an account reads that someone else wrote: received email with its attachments, texts, voicemail, what is said on a call or in a meeting, page text from the browser, output from the workspace, results from paid tools, files on the drive, and what is written to memory.
Deliver flagged content that is only a warning, but keep withholding criticals.The client calls stack_set_flagged_content_settings. From code or the terminal:
await stack.flaggedContent.set({ warning: 'deliver', critical: 'withhold' });npx @getstackrun/cli flagged-content set --warning deliver --critical withhold
npx @getstackrun/cli flagged-content getWhat has been flagged for the assistant agent?The client calls stack_list_security_events. Every account can see this list, with controls on or off.
npx @getstackrun/cli event list --agent agt_123
npx @getstackrun/cli event show <event-id>
npx @getstackrun/cli event resolve <event-id>
# Clear an agent's open warnings in one go.
npx @getstackrun/cli agent dismiss-warnings agt_123const result = await stack.scan.scan({ content: text, context: 'webpage' });
// result.verdict: clean, suspicious or criticalThe tool is stack_scan, and from the terminal scan --file <path>. Use it for content your own code fetched before you hand it to an agent. Each scan is one action.
npx @getstackrun/cli detector list
npx @getstackrun/cli detector configure <detector-key> --from-file ./config.json
npx @getstackrun/cli detector reset <detector-key>Switching a detector off, or listing something as a false positive, removes a signal. It gives an agent no new access.
Flagged content from outside never blocks an agent. An agent you registered to be blocked on a critical finding about its own behaviour stays blocked until you unblock it: agent unblock <agent>, or stack_unblock_agent. Unblocking asks for your approval.
Every detector is described in Detectors. The events are on Security Events.