dbcve.org
Missing AuthenticationWeakness · CWE-306

CVE-2026-57495

HIGH · 8.2 CVSS v4.0 Published 2026-07-20
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
91/100
Remediation priority · Urgent
Remotely reachable No privileges Zero-click 4 weeks old

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
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.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · high confidence

In @agenticmail packages prior to versions 0.2.39/0.1.33/0.9.43/0.5.71, two inbound-mail handlers (bridge-wake path) resume Claude Code sessions with bypassPermissions without verifying the sender is the operator, unlike a sibling handler that properly uses isOperatorReplySender(). External emails inject attacker-controlled from/subject/preview into the prompt of a fully-privileged agent running as the operator's OAuth identity.

MitigationUpgrade to patched versions (claudecode 0.2.39, codex 0.1.33, core 0.9.43, openclaw 0.5.71) or implement sender verification similar to the sibling operator-reply handler before processing privileged effects.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
High
Privileges
None
Authentication
X
User interaction
None
Scope
X

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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Check installed AgenticMail package versions
    Run `npm list @agenticmail/claudecode @agenticmail/codex @agenticmail/core @agenticmail/openclaw` to list installed versions
    Affected if Installed version is lower than 0.2.39 (claudecode), 0.1.33 (codex), 0.9.43 (core), or 0.5.71 (openclaw)
  2. Locate the bridge-wake handler source
    Search project files for 'bridge-wake' handler definition, typically in dispatcher or bridge modules
    Affected if The bridge-wake handler file exists in the codebase
  3. Verify authorization check in bridge-wake handler
    Open the bridge-wake handler source file and search for `isOperatorReplySender` function call within that handler
    Affected if The bridge-wake handler does NOT contain a call to `isOperatorReplySender()` for sender verification
  4. Check for vulnerable permissionMode usage
    Search the bridge-wake handler code for `permissionMode: 'bypassPermissions'` being set when resuming sessions
    Affected if The bridge-wake handler sets `permissionMode: 'bypassPermissions'` without prior operator sender verification
  5. Inspect email field injection points
    Examine how external email fields (from/subject/preview) are passed into prompts or session resume calls in the bridge-wake handler
    Affected if External email fields are directly embedded into prompts without sanitization or operator verification

If the bridge-wake handler is present, lacks `isOperatorReplySender()` verification, and uses `permissionMode: 'bypassPermissions'` for externally-sourced emails, the environment is vulnerable to CVE-2026-57495.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

dbcve · scoped
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Upgrade to patched versions (claudecode 0.2.39, codex 0.1.33, core 0.9.43, openclaw 0.5.71) or implement sender verification similar to the sibling operator-reply handler before processing privileged effects.

Recommended fix High confidence

Upgrade to @agenticmail/claudecode 0.2.39, @agenticmail/codex 0.1.33, @agenticmail/core 0.9.43, and @agenticmail/openclaw 0.5.71

  1. Identify which @agenticmail packages (@agenticmail/claudecode, @agenticmail/codex, @agenticmail/core, @agenticmail/openclaw) are installed in the project
  2. Run npm list to confirm current installed versions of each affected package
  3. For each affected package, run npm install @agenticmail/[email protected] @agenticmail/[email protected] @agenticmail/[email protected] @agenticmail/[email protected] (or use appropriate package manager command)
  4. Verify the upgrades were successful by running npm list again to confirm the new versions are installed
  5. Rebuild/redeploy the application to ensure the fixed code is running
  6. Test that incoming email handling now properly validates the sender is the operator before acting on privileged effects

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation3.0 h
  • Implementation4.0 h
  • Testing3.0 h
  • Review / QA2.0 h
12.0 hours of engineering $2,130
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,408.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-57495 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-57495 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data