CVE-2026-57495

HIGHPre-NVD 8.28.2—
EchelonGraph scoreMEDIUM confidence

This high-severity CVE scores 8.2 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.3%, top 80% of all CVEs by exploit prediction. GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).

Triggered by: NVD CVSS baseline
Sources: epss, secondary
Trending — 3 sources updated this week
8.2
EchelonGraph verdictPlan a fixSerious severity, but no confirmed exploitation yet.
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS: 0%CVSS: 8.2Exploit: NoneExposed: 0

No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.

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 v3
8.2
EG Score
8.2(medium)
EG Risk
52(Track)
EG Risk 52/100SSVC: Track

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed
Severity82% × 45%
Exploitation0% × 40%
Automatability100% × 15%
Action: Routine — remediate on your standard cadence.
EPSS
20.3%
KEV
Not listed

Published

July 20, 2026

Last Modified

July 23, 2026

Advisory Details (1)

Auto-updated Jul 20, 2026
🔬 Proof of concept available. Patch available. Sources: github.
github Patch Available🟡 PoC Available

Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake) with no sender gate, while the sibling operator-query hook authenticates the sender (CWE-306) · Advisory · agenticmail/agenticmail · GitHub

https://github.com/agenticmail/agenticmail/security/advisories/GHSA-fq4x-789w-jg5h

Vendor Advisories for CVE-2026-57495(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Affected Packages

(4 across 1 ecosystem)
npm(4)
PackageVulnerable rangeFixed inDependents
@agenticmail/claudecode—0.2.39—
@agenticmail/codex—0.1.33—
@agenticmail/core—0.9.43—
@agenticmail/openclaw—0.5.71—

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 10× in last 7d / 10× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-07-23 14:18 UTCEPSS rescore
  2. 2026-07-23 14:18 UTCEPSS rescore
  3. 2026-07-23 03:20 UTCEG score recompute
  4. 2026-07-22 23:27 UTCEG score recompute
  5. 2026-07-22 14:08 UTCEPSS rescore
  6. 2026-07-22 14:08 UTCEPSS rescore
  7. 2026-07-21 15:25 UTCEPSS rescore
  8. 2026-07-20 22:42 UTCEG score recompute
  9. 2026-07-20 22:12 UTCEG score recompute
  10. 2026-07-20 22:12 UTCMITRE cvelistV5first tracked

Frequently asked(5)

What is CVE-2026-57495?
CVE-2026-57495 is a high vulnerability published on July 20, 2026. 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…
When was CVE-2026-57495 disclosed?
CVE-2026-57495 was first published in the National Vulnerability Database on July 20, 2026, with the most recent update on July 23, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-57495 actively exploited?
CVE-2026-57495 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 20.3% percentile likelihood of exploitation in the next 30 days — higher percentiles indicate greater predicted risk.
What is the CVSS score of CVE-2026-57495?
CVE-2026-57495 has a CVSS v3 base score of 8.2 (NVD).
How do I remediate CVE-2026-57495?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-57495, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-57495

Explore →

Is Your Infrastructure Affected by CVE-2026-57495?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Start Free Scan →Browse All CVEs