{"cve":"CVE-2026-57495","nvd":{"published":"2026-07-20T22:17:17.107","modified":"2026-07-23T15:54:18.643","status":"Deferred","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.","cvss_v4":{"vector":"CVSS:4.0/AV:N/AC:H/AT:N/PR:N/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N","score":8.2},"cvss_v3":null,"cwes":["CWE-306"],"references":["https://github.com/agenticmail/agenticmail/security/advisories/GHSA-fq4x-789w-jg5h"],"products":[],"source":"nvd","synced_at":"2026-10-19T22:45:36.895656543+00:00"},"epss":{"cve":"CVE-2026-57495","score":0.00362,"percentile":0.30065,"date":"2026-10-31"},"kev":null,"osv":[{"id":"GHSA-fq4x-789w-jg5h","url":"https://osv.dev/vulnerability/GHSA-fq4x-789w-jg5h","summary":"AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)","modified":"2026-07-21T13:56:44.272818Z","packages":[{"ecosystem":"npm","name":"@agenticmail/core","purl":"pkg:npm/%40agenticmail/core","ranges":["<0.9.43"],"fixed":["0.9.43"]},{"ecosystem":"npm","name":"@agenticmail/claudecode","purl":"pkg:npm/%40agenticmail/claudecode","ranges":["<0.2.39"],"fixed":["0.2.39"]},{"ecosystem":"npm","name":"@agenticmail/codex","purl":"pkg:npm/%40agenticmail/codex","ranges":["<0.1.33"],"fixed":["0.1.33"]},{"ecosystem":"npm","name":"@agenticmail/openclaw","purl":"pkg:npm/%40agenticmail/openclaw","ranges":["<0.5.71"],"fixed":["0.5.71"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}