AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)

Summary

AgenticMail gives AI agents real email addresses and phone numbers. In @agenticmail/claudecode prior to version 0.2.39, @agenticmail/codex prior to version 0.1.33, @agenticmail/core prior to version 0.9.43, and @agenticmail/openclaw prior to version 0.5.71, two inbound-mail handlers act on a privileged effect without verifying that the sender is the operator, while a sibling handler in the same repo does. The higher-impact one: any external email routed to the bridge inbox causes the dispatcher to resume the operator's Claude Code session with `permissionMode: 'bypassPermissions'`, embedding the attacker-controlled `from`/`subject`/`preview` verbatim into the prompt the resumed agent reads — an indirect prompt injection into a fully-privileged agent (Bash/Write/Edit/WebFetch + the agenticmail MCP toolbelt) running as the operator's OAuth identity. The sibling operator-query email-reply hook gates the same untrusted-From provenance with `isOperatorReplySender(replyFrom, config.operatorEmail)` (fail-closed); the bridge-wake path — a strictly higher-privilege effect — has no equivalent. @agenticmail/claudecode 0.2.39, @agenticmail/codex 0.1.33, @agenticmail/core 0.9.43, and @agenticmail/openclaw 0.5.71 contain a fix.

Timeline

1. Jul 20, 2026, 10:09 PM UTCCVE published
2. Jul 22, 2026, 1:53 PM UTCCISA SSVC assessment

   Exploitation: none · Automatable: yes · Technical impact: total

3. Jul 22, 2026, 1:53 PM UTCRecord last updated

Affected versions

• agenticmail @agenticmail/core

  fixed in 0.9.43

• agenticmail @agenticmail/claudecode

  fixed in 0.2.39

• agenticmail @agenticmail/codex

  fixed in 0.1.33

• agenticmail @agenticmail/openclaw

  fixed in 0.5.71

• @agenticmail/corenpm

  fixed in 0.9.43

• @agenticmail/claudecodenpm

  fixed in 0.2.39

• @agenticmail/codexnpm

  fixed in 0.1.33

• @agenticmail/openclawnpm

  fixed in 0.5.71

References 1