Track vulnerabilities like this one. Sign up free to get alerted when software you use is affected.
8.2

AgenticMail: Untrusted Emails Resume Operator's Session

CVE-2026-57495 · published 3 months ago
Summary

AgenticMail's Claude Code session can be resumed by untrusted emails, potentially allowing attackers to inject malicious prompts into a fully-privileged agent. This affects versions of AgenticMail's core libraries prior to 0.2.39, 0.1.33, 0.9.43, and 0.5.71. Update to the latest versions of these libraries to fix the issue.

What to do

The CVE record does not list a fixed version. Check the vendor's site or the advisory links below - a fix may already be released.

Affected software
VendorProductAffected versions
agenticmail @agenticmail/core < 0.9.43
agenticmail @agenticmail/claudecode < 0.2.39
agenticmail @agenticmail/codex < 0.1.33
agenticmail @agenticmail/openclaw < 0.5.71
Original advisory text
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 versio...
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.
References
Fix within
Internet-facing 3 days
Internal 60 days
  • Not known to be exploited
  • Can be exploited automatically
  • Gives an attacker full control
Severity
8.2 High
Exploitation
<1% chance of attack within 30 days
Type
CWE-306Missing Authentication for Critical Function
Timeline
Published20 Jul 2026
Updated4 Nov 2026
First seen20 Jul 2026
Sources
CVE-2026-57495 · NVD
CVE-2026-57495 · MITRE
Track software like this
Free during beta