Search
Find a vulnerability
Search criteria
2 vulnerabilities found for @agenticmail/codex by agenticmail
CVE-2026-57495 (GCVE-0-2026-57495)
Vulnerability from nvd – Published: 2026-07-20 22:09 – Updated: 2026-07-20 22:09
VLAI
EPSS
VEX
Title
AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)
Summary
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.
Severity
CWE
- CWE-306 - Missing Authentication for Critical Function
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/agenticmail/agenticmail/securi… | x_refsource_CONFIRM |
Impacted products
4 products
| Vendor | Product | Version | |
|---|---|---|---|
| agenticmail | @agenticmail/core |
Affected:
< 0.9.43
|
|
| agenticmail | @agenticmail/claudecode |
Affected:
< 0.2.39
|
|
| agenticmail | @agenticmail/codex |
Affected:
< 0.1.33
|
|
| agenticmail | @agenticmail/openclaw |
Affected:
< 0.5.71
|
{
"containers": {
"cna": {
"affected": [
{
"product": "@agenticmail/core",
"vendor": "agenticmail",
"versions": [
{
"status": "affected",
"version": "\u003c 0.9.43"
}
]
},
{
"product": "@agenticmail/claudecode",
"vendor": "agenticmail",
"versions": [
{
"status": "affected",
"version": "\u003c 0.2.39"
}
]
},
{
"product": "@agenticmail/codex",
"vendor": "agenticmail",
"versions": [
{
"status": "affected",
"version": "\u003c 0.1.33"
}
]
},
{
"product": "@agenticmail/openclaw",
"vendor": "agenticmail",
"versions": [
{
"status": "affected",
"version": "\u003c 0.5.71"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "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\u0027s Claude Code session with `permissionMode: \u0027bypassPermissions\u0027`, embedding the attacker-controlled `from`/`subject`/`preview` verbatim into the prompt the resumed agent reads \u2014 an indirect prompt injection into a fully-privileged agent (Bash/Write/Edit/WebFetch + the agenticmail MCP toolbelt) running as the operator\u0027s 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 \u2014 a strictly higher-privilege effect \u2014 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."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "HIGH",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.2,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "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",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "HIGH"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-306",
"description": "CWE-306: Missing Authentication for Critical Function",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-20T22:09:54.001Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/agenticmail/agenticmail/security/advisories/GHSA-fq4x-789w-jg5h",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/agenticmail/agenticmail/security/advisories/GHSA-fq4x-789w-jg5h"
}
],
"source": {
"advisory": "GHSA-fq4x-789w-jg5h",
"discovery": "UNKNOWN"
},
"title": "AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator\u0027s Claude Code session (bridge-wake)"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-57495",
"datePublished": "2026-07-20T22:09:54.001Z",
"dateReserved": "2026-06-24T14:53:40.111Z",
"dateUpdated": "2026-07-20T22:09:54.001Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
CVE-2026-57495 (GCVE-0-2026-57495)
Vulnerability from cvelistv5 – Published: 2026-07-20 22:09 – Updated: 2026-07-20 22:09
VLAI
EPSS
VEX
Title
AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator's Claude Code session (bridge-wake)
Summary
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.
Severity
CWE
- CWE-306 - Missing Authentication for Critical Function
Assigner
References
1 reference
| URL | Tags |
|---|---|
| https://github.com/agenticmail/agenticmail/securi… | x_refsource_CONFIRM |
Impacted products
4 products
| Vendor | Product | Version | |
|---|---|---|---|
| agenticmail | @agenticmail/core |
Affected:
< 0.9.43
|
|
| agenticmail | @agenticmail/claudecode |
Affected:
< 0.2.39
|
|
| agenticmail | @agenticmail/codex |
Affected:
< 0.1.33
|
|
| agenticmail | @agenticmail/openclaw |
Affected:
< 0.5.71
|
{
"containers": {
"cna": {
"affected": [
{
"product": "@agenticmail/core",
"vendor": "agenticmail",
"versions": [
{
"status": "affected",
"version": "\u003c 0.9.43"
}
]
},
{
"product": "@agenticmail/claudecode",
"vendor": "agenticmail",
"versions": [
{
"status": "affected",
"version": "\u003c 0.2.39"
}
]
},
{
"product": "@agenticmail/codex",
"vendor": "agenticmail",
"versions": [
{
"status": "affected",
"version": "\u003c 0.1.33"
}
]
},
{
"product": "@agenticmail/openclaw",
"vendor": "agenticmail",
"versions": [
{
"status": "affected",
"version": "\u003c 0.5.71"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "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\u0027s Claude Code session with `permissionMode: \u0027bypassPermissions\u0027`, embedding the attacker-controlled `from`/`subject`/`preview` verbatim into the prompt the resumed agent reads \u2014 an indirect prompt injection into a fully-privileged agent (Bash/Write/Edit/WebFetch + the agenticmail MCP toolbelt) running as the operator\u0027s 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 \u2014 a strictly higher-privilege effect \u2014 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."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "HIGH",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 8.2,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "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",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "HIGH"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-306",
"description": "CWE-306: Missing Authentication for Critical Function",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-07-20T22:09:54.001Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/agenticmail/agenticmail/security/advisories/GHSA-fq4x-789w-jg5h",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/agenticmail/agenticmail/security/advisories/GHSA-fq4x-789w-jg5h"
}
],
"source": {
"advisory": "GHSA-fq4x-789w-jg5h",
"discovery": "UNKNOWN"
},
"title": "AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator\u0027s Claude Code session (bridge-wake)"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-57495",
"datePublished": "2026-07-20T22:09:54.001Z",
"dateReserved": "2026-06-24T14:53:40.111Z",
"dateUpdated": "2026-07-20T22:09:54.001Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}