CVE-2026-57495 AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)
Unauthenticated inbound emails trigger privileged AI agent sessions with bypassed permissions, allowing attackers to execute arbitrary code via prompt injection.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-57495?
CVE-2026-57495 is a high-severity missing authorization vulnerability in @agenticmail/claudecode, published on 20 Jul 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Weakness: CWE-306
Which versions are affected by CVE-2026-57495?
8 open source packages ship an affected version, including @agenticmail/claudecode, @agenticmail/codex and @agenticmail/core.
| Package | Affected | Fixed in |
|---|---|---|
@agenticmail/claudecode npm | All versions | 0.2.39 |
@agenticmail/claudecode npm | All versions | 0.2.39 |
@agenticmail/codex npm | All versions | 0.1.33 |
@agenticmail/codex npm | All versions | 0.1.33 |
@agenticmail/core npm | All versions | 0.9.43 |
@agenticmail/core npm | All versions | 0.9.43 |
2 more packages
@agenticmail/openclaw npm | All versions | 0.5.71 |
@agenticmail/openclaw npm | All versions | 0.5.71 |
How do I fix CVE-2026-57495?
Upgrade @agenticmail/claudecode to 0.2.39 or later.
Upgrade, and check permissions on every request on the server, not only in the interface. More about Missing authorization.
Is CVE-2026-57495 being exploited?
There is no known exploitation of CVE-2026-57495 in the wild and no public exploit code.
Sources
Also known as GHSA-fq4x-789w-jg5h.