CVE-2026-57495 AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- No known exploitation · automatable: yes · technical impact: total
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.
Upgrade path
8 packages: 4 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| agenticmail @agenticmail/claudecode(npm) | < 0.2.39 | 0.2.39 | Fixed |
| agenticmail @agenticmail/codex(npm) | < 0.1.33 | 0.1.33 | Fixed |
| agenticmail @agenticmail/core(npm) | < 0.9.43 | 0.9.43 | Fixed |
| agenticmail @agenticmail/openclaw(npm) | < 0.5.71 | 0.5.71 | Fixed |
| agenticmail @agenticmail/claudecode | = < 0.2.39 | No fix listed | Versions listed |
| agenticmail @agenticmail/codex | = < 0.1.33 | No fix listed | Versions listed |
| agenticmail @agenticmail/core | = < 0.9.43 | No fix listed | Versions listed |
| agenticmail @agenticmail/openclaw | = < 0.5.71 | No fix listed | Versions listed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| agenticmail @agenticmail/core | = < 0.9.43 | No fix listed |
| agenticmail @agenticmail/claudecode | = < 0.2.39 | No fix listed |
| agenticmail @agenticmail/codex | = < 0.1.33 | No fix listed |
| agenticmail @agenticmail/openclaw | = < 0.5.71 | No fix listed |
| agenticmail @agenticmail/core(npm) | < 0.9.43 | 0.9.43 |
| agenticmail @agenticmail/claudecode(npm) | < 0.2.39 | 0.2.39 |
| agenticmail @agenticmail/codex(npm) | < 0.1.33 | 0.1.33 |
| agenticmail @agenticmail/openclaw(npm) | < 0.5.71 | 0.5.71 |
References
- https://github.com/agenticmail/agenticmail/security/advisories/GHSA-fq4x-789w-jg5h vendor-advisory
- nvd.nist.gov third-party-advisory vendor-advisory
- github.com
- github.com product