GHSA-FQ4X-789W-JG5H
Vulnerability from github – Published: 2026-06-18 17:21 – Updated: 2026-07-21 13:41Summary
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.
Affected code (current HEAD, commit b95f52e)
Untrusted provenance: external inbound email enters at packages/api/src/routes/inbound.ts:41 (POST /mail/inbound); the x-inbound-secret authenticates only the relay->API hop, not the external sender, so from/subject/preview are attacker-controlled.
Privileged sink (bridge-wake, bypassPermissions):
- packages/claudecode/src/dispatcher.ts:2040 handleBridgeMail extracts subject/from/preview (:2045-2049) and calls planBridgeWake({ session, mail: { ..., from, preview } }) (:2052) with NO sender check — routing keys only on session freshness (skip-live / escalate / resume).
- planBridgeWake -> packages/core/src/host-bridge.ts:141 composeBridgeWakePrompt embeds the untrusted from/subject/preview (preview sliced to 600 chars at :144) verbatim into the prompt.
- packages/claudecode/src/bridge-wake.ts:103 resumeBridgeSession runs the prompt via the Claude Code SDK with permissionMode: 'bypassPermissions' against the operator's last session (resume + same mcpServers).
Guarded sibling (same class, authenticated): packages/api/src/routes/inbound.ts:102 rejects an operator-query email reply unless isOperatorReplySender(replyFrom, config.operatorEmail) (def packages/core/src/phone/realtime-tools.ts:999, fail-closed when no operatorEmail), with a v0.9.53 security-review comment (inbound.ts:93-100) stating inbound mail provenance is untrusted and an emailed answer is only honored when its From matches the configured operator. The Telegram sibling likewise gates on operatorChatId. The bridge-wake path ignores this exact lesson.
Secondary instance (same root cause): packages/core/src/gateway/manager.ts:261 tryProcessApprovalReply releases a held outbound email on an "approve" reply matched only by In-Reply-To / notification_message_id, with no sender check — again unlike the isOperatorReplySender sibling.
Impact
In a configured headless-bridge deployment (operator uses the CLI so a host-session is saved; session fresh <24h per host-sessions.ts:127; external mail routed to the bridge inbox via relay sub-addressing or a Cloudflare webhook), an external sender achieves indirect prompt injection into a bypassPermissions operator session -> arbitrary OS command execution, filesystem read/write, and exfiltration under the operator's OAuth identity. The auth gap (no sender check on the bridge path) is structural and unconditional; the impact realization is config-conditional and depends on the resumed model following injected instructions.
Proof of concept (static / request-difference; dynamic on operator's OWN setup only)
Static: the from/subject/preview extracted at dispatcher.ts:2045-2049 flow into composeBridgeWakePrompt (host-bridge.ts:141) and resumeBridgeSession (bridge-wake.ts:103) with no interposed sender check, while the sibling inbound.ts:102 has one — the same untrusted-From provenance is authenticated on one privileged email path and not on the higher-privileged one. Dynamic (own instance only): with a configured bridge + fresh host-session, send mail from a non-operator address into the bridge inbox whose subject/preview contains a benign instruction writing a fresh CSPRNG marker; observe the resumed bypassPermissions session act on it. Use only your own instance; do not target third-party deployments.
Suggested fix
Mirror the guarded sibling: before any bypassPermissions resume (dispatcher.ts handleBridgeMail, before planBridgeWake), require trusted provenance — an internal sub-agent wake OR isOperatorReplySender(from, config.operatorEmail); otherwise deliver the mail normally but do NOT resume. Reuse the existing exported isOperatorReplySender from @agenticmail/core so the two privileged email paths share one authentication helper. Defense-in-depth: in composeBridgeWakePrompt, wrap the untrusted fields in explicit untrusted-data delimiters and drop bypassPermissions for mail-triggered resumes whose provenance is not the operator. Apply the same sender gate to tryProcessApprovalReply (manager.ts:261).
Affected versions
Present on current HEAD (core 0.9.42 / claudecode 0.2.38, commit b95f52e). No fix retrofits the sender check onto bridge-wake.
Severity (honest, both ways)
HIGH, plausibly CRITICAL in a configured headless-bridge deployment. Ceiling ~9.0 (unauthenticated external sender -> operator-privileged code execution). Floor ~7.0: the auth gap is unconditional, but full impact requires (1) a fresh <24h host-session, (2) external mail routed to the bridge inbox, (3) the resumed model obeying injected instructions (non-deterministic). Not a deterministic RCE primitive. CWE-306 (missing authentication for the privileged action) + CWE-77/CWE-94 (injected instructions realized as command execution). Novelty: the two existing agenticmail advisories (CVE-2026-50287 MCP missing-auth; CVE-2026-47255 storage SQL) do not cover this sink. Please rate per your deployment assumptions.
{
"affected": [
{
"package": {
"ecosystem": "npm",
"name": "@agenticmail/core"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.9.43"
}
],
"type": "ECOSYSTEM"
}
]
},
{
"package": {
"ecosystem": "npm",
"name": "@agenticmail/claudecode"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.2.39"
}
],
"type": "ECOSYSTEM"
}
]
},
{
"package": {
"ecosystem": "npm",
"name": "@agenticmail/codex"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.1.33"
}
],
"type": "ECOSYSTEM"
}
]
},
{
"package": {
"ecosystem": "npm",
"name": "@agenticmail/openclaw"
},
"ranges": [
{
"events": [
{
"introduced": "0"
},
{
"fixed": "0.5.71"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"aliases": [
"CVE-2026-57495"
],
"database_specific": {
"cwe_ids": [
"CWE-306"
],
"github_reviewed": true,
"github_reviewed_at": "2026-06-18T17:21:27Z",
"nvd_published_at": "2026-07-20T22:17:17Z",
"severity": "HIGH"
},
"details": "## Summary\nTwo 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.\n\n## Affected code (current HEAD, commit b95f52e)\nUntrusted provenance: external inbound email enters at `packages/api/src/routes/inbound.ts:41` (POST /mail/inbound); the `x-inbound-secret` authenticates only the relay-\u003eAPI hop, not the external sender, so `from`/`subject`/`preview` are attacker-controlled.\n\nPrivileged sink (bridge-wake, bypassPermissions):\n- `packages/claudecode/src/dispatcher.ts:2040` `handleBridgeMail` extracts `subject`/`from`/`preview` (`:2045-2049`) and calls `planBridgeWake({ session, mail: { ..., from, preview } })` (`:2052`) with NO sender check \u2014 routing keys only on session freshness (skip-live / escalate / resume).\n- `planBridgeWake` -\u003e `packages/core/src/host-bridge.ts:141` `composeBridgeWakePrompt` embeds the untrusted `from`/`subject`/`preview` (preview sliced to 600 chars at `:144`) verbatim into the prompt.\n- `packages/claudecode/src/bridge-wake.ts:103` `resumeBridgeSession` runs the prompt via the Claude Code SDK with `permissionMode: \u0027bypassPermissions\u0027` against the operator\u0027s last session (resume + same mcpServers).\n\nGuarded sibling (same class, authenticated): `packages/api/src/routes/inbound.ts:102` rejects an operator-query email reply unless `isOperatorReplySender(replyFrom, config.operatorEmail)` (def `packages/core/src/phone/realtime-tools.ts:999`, fail-closed when no operatorEmail), with a v0.9.53 security-review comment (`inbound.ts:93-100`) stating inbound mail provenance is untrusted and an emailed answer is only honored when its From matches the configured operator. The Telegram sibling likewise gates on `operatorChatId`. The bridge-wake path ignores this exact lesson.\n\nSecondary instance (same root cause): `packages/core/src/gateway/manager.ts:261` `tryProcessApprovalReply` releases a held outbound email on an \"approve\" reply matched only by `In-Reply-To` / `notification_message_id`, with no sender check \u2014 again unlike the `isOperatorReplySender` sibling.\n\n## Impact\nIn a configured headless-bridge deployment (operator uses the CLI so a host-session is saved; session fresh \u003c24h per `host-sessions.ts:127`; external mail routed to the bridge inbox via relay sub-addressing or a Cloudflare webhook), an external sender achieves indirect prompt injection into a `bypassPermissions` operator session -\u003e arbitrary OS command execution, filesystem read/write, and exfiltration under the operator\u0027s OAuth identity. The auth gap (no sender check on the bridge path) is structural and unconditional; the impact realization is config-conditional and depends on the resumed model following injected instructions.\n\n## Proof of concept (static / request-difference; dynamic on operator\u0027s OWN setup only)\nStatic: the from/subject/preview extracted at dispatcher.ts:2045-2049 flow into composeBridgeWakePrompt (host-bridge.ts:141) and resumeBridgeSession (bridge-wake.ts:103) with no interposed sender check, while the sibling inbound.ts:102 has one \u2014 the same untrusted-From provenance is authenticated on one privileged email path and not on the higher-privileged one. Dynamic (own instance only): with a configured bridge + fresh host-session, send mail from a non-operator address into the bridge inbox whose subject/preview contains a benign instruction writing a fresh CSPRNG marker; observe the resumed bypassPermissions session act on it. Use only your own instance; do not target third-party deployments.\n\n## Suggested fix\nMirror the guarded sibling: before any `bypassPermissions` resume (dispatcher.ts handleBridgeMail, before planBridgeWake), require trusted provenance \u2014 an internal sub-agent wake OR `isOperatorReplySender(from, config.operatorEmail)`; otherwise deliver the mail normally but do NOT resume. Reuse the existing exported `isOperatorReplySender` from @agenticmail/core so the two privileged email paths share one authentication helper. Defense-in-depth: in composeBridgeWakePrompt, wrap the untrusted fields in explicit untrusted-data delimiters and drop `bypassPermissions` for mail-triggered resumes whose provenance is not the operator. Apply the same sender gate to `tryProcessApprovalReply` (manager.ts:261).\n\n## Affected versions\nPresent on current HEAD (core 0.9.42 / claudecode 0.2.38, commit b95f52e). No fix retrofits the sender check onto bridge-wake.\n\n## Severity (honest, both ways)\nHIGH, plausibly CRITICAL in a configured headless-bridge deployment. Ceiling ~9.0 (unauthenticated external sender -\u003e operator-privileged code execution). Floor ~7.0: the auth gap is unconditional, but full impact requires (1) a fresh \u003c24h host-session, (2) external mail routed to the bridge inbox, (3) the resumed model obeying injected instructions (non-deterministic). Not a deterministic RCE primitive. CWE-306 (missing authentication for the privileged action) + CWE-77/CWE-94 (injected instructions realized as command execution). Novelty: the two existing agenticmail advisories (CVE-2026-50287 MCP missing-auth; CVE-2026-47255 storage SQL) do not cover this sink. Please rate per your deployment assumptions.",
"id": "GHSA-fq4x-789w-jg5h",
"modified": "2026-07-21T13:41:07Z",
"published": "2026-06-18T17:21:27Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/agenticmail/agenticmail/security/advisories/GHSA-fq4x-789w-jg5h"
},
{
"type": "ADVISORY",
"url": "https://nvd.nist.gov/vuln/detail/CVE-2026-57495"
},
{
"type": "PACKAGE",
"url": "https://github.com/agenticmail/agenticmail"
}
],
"schema_version": "1.4.0",
"severity": [
{
"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",
"type": "CVSS_V4"
}
],
"summary": "AgenticMail: Unauthenticated inbound mail triggers bypassPermissions resume of the operator\u0027s Claude Code session (bridge-wake)"
}
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
Loading timeline…
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.