Threat Pulse · Deep dive
PII leak attempt
The agent tried to send personal data, emails, IDs, or phone numbers, outside your boundary, often hidden inside an otherwise innocent-looking message.
How we stop it
Outbound content is scanned for PII patterns before it leaves. Matches are blocked, redacted from logs, and the attempt is recorded.
Frequently asked
What is pii leak attempt?
The agent tried to send personal data, emails, IDs, or phone numbers, outside your boundary, often hidden inside an otherwise innocent-looking message.
How does Rogue-Agent Defense stop pii leak attempt?
Outbound content is scanned for PII patterns before it leaves. Matches are blocked, redacted from logs, and the attempt is recorded.
What should I do if I see pii leak attempt in the Threat Pulse feed?
Nothing urgent: the feed only shows attacks that were already blocked or flagged. If one class keeps appearing, review the linked defense guide and check your agents' allowlists, data boundaries, and spend caps.
Counts are real enforcement rows, anonymized. Attack classes seen in fewer than three workspaces never get a page.