https://vulnerability.circl.lu Contains only the most 10 recent entries. http://www.rssboard.org/rss-specification python-feedgen en Sun, 04 Oct 2026 06:16:08 +0000 https://vulnerability.circl.lu/vuln/fkie_cve-2026-57495 <p>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&#39;s Claude Code session with `permissionMode: &#39;bypassPermissions&#39;`, 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&#39;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.</p> <p>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&#39;s Claude Code session with `permissionMode: &#39;bypassPermissions&#39;`, 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&#39;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.</p> https://vulnerability.circl.lu/vuln/fkie_cve-2026-57495 https://vulnerability.circl.lu/vuln/ghsa-fq4x-789w-jg5h <p><strong>Affected:</strong> npm: @agenticmail/core, npm: @agenticmail/claudecode, npm: @agenticmail/codex, npm: @agenticmail/openclaw</p> <p>## Summary 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&#39;s Claude Code session with `permissionMode: &#39;bypassPermissions&#39;`, 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&#39;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.</p> <p>## 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-&gt;API hop, not the external sender, so `from`/`subject`/`preview` are attacker-controlled.</p> <p>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 / res…</p> <p><strong>Affected:</strong> npm: @agenticmail/core, npm: @agenticmail/claudecode, npm: @agenticmail/codex, npm: @agenticmail/openclaw</p> <p>## Summary 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&#39;s Claude Code session with `permissionMode: &#39;bypassPermissions&#39;`, 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&#39;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.</p> <p>## 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-&gt;API hop, not the external sender, so `from`/`subject`/`preview` are attacker-controlled.</p> <p>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 / res…</p> https://vulnerability.circl.lu/vuln/ghsa-fq4x-789w-jg5h