Threadlinqs IntelligenceStart free

VulnerabilityCVE-2026-57495Published 2026-07-20

CVE-2026-57495 — agenticmail @agenticmail/core

high (derived)

As of 2026-07-20, CVE-2026-57495 is a High-severity (band derived from the CVSS v4.0 score, not stated by the CNA) vulnerability in agenticmail @agenticmail/core, CVSS v4.0 8.2, EPSS 0.2% (20.2th percentile). No Threadlinqs-tracked threat campaign has been attributed to CVE-2026-57495 as of 2026-07-20; the identifier is re-checked against the Threadlinqs threat corpus on every daily ingest.

CVSS v4.0
8.2/10High (derived)
EPSS
0.2%Higher than 20.2% of scored CVEs
CISA KEV
NoNot in the KEV catalog
Tracked threats
0None linked yet
Priority
4.9/10Threadlinqs triage score
Published
CVSS v4.0 8.2 (High, derived from score) · EPSS 0.2% (higher than 20.2% of all scored CVEs) · Priority 4.9/10 · Published 2026-07-20

Last updated:

What is CVE-2026-57495?

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.

The record classifies CVE-2026-57495 under weakness class CWE-306. 4 affected-product entries are recorded, across 1 vendor, listed below. The identifier was first published 122 days ago.

Severity and exploitation probability

CVSS v4.0 base score
8.2 — High (derived from score)
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
EPSS (FIRST)
0.2% probability of exploitation in the next 30 days, higher than 20.2% of all scored CVEs
CISA KEV
Not listed in the CISA Known Exploited Vulnerabilities catalog
Threadlinqs priority
4.9/10 — a Threadlinqs composite of the CVSS base score, the EPSS percentile and public exploit availability
Published
2026-07-20

Is CVE-2026-57495 being exploited?

It currently carries a trending score of 35 in the Threadlinqs vulnerability feed.

Affected products and versions

  • agenticmail: @agenticmail/core, @agenticmail/claudecode, @agenticmail/codex, @agenticmail/openclaw

Affected software packages:

  • npm:@agenticmail/core — patched in 0.9.43
  • npm:@agenticmail/claudecode — patched in 0.2.39
  • npm:@agenticmail/codex — patched in 0.1.33
  • npm:@agenticmail/openclaw — patched in 0.5.71

How to fix CVE-2026-57495

Fixed versions are recorded for 4 packages: npm:@agenticmail/core 0.9.43, npm:@agenticmail/claudecode 0.2.39, npm:@agenticmail/codex 0.1.33, npm:@agenticmail/openclaw 0.5.71. No vendor patch reference has been recorded for CVE-2026-57495 in the tracked sources. Follow the references below for a fix, and treat the products listed above as exposed until the vendor states otherwise.

Threat activity tracking CVE-2026-57495

No threat campaign in the Threadlinqs corpus currently references CVE-2026-57495, in its CVE list or as an indicator. The linkage is recomputed from the live corpus on every daily ingest, so this section fills in as soon as a tracked campaign cites the identifier.

Sources

Enriched from CVE.org, NVD, FIRST EPSS, GitHub Security Advisories. This product uses the NVD API but is not endorsed or certified by the NVD.

Vendor advisory and patch