CVE-2026-57495
External email can prompt-inject and resume a privileged AI agent as the operator.
Is CVE-2026-57495 being exploited?
Not confirmed. CVE-2026-57495 does not appear in CISA's Known Exploited Vulnerabilities catalog, which records only exploitation that has been observed and reported publicly. That is evidence of absence of a report, not evidence the flaw is unattacked. EPSS currently estimates a 0.36% probability of exploitation in the next 30 days.
How severe is CVE-2026-57495?
CVE-2026-57495 is rated High with a CVSS score of 8.2. Severity describes how bad exploitation would be, not how likely it is: pair it with exploitation evidence before deciding what to patch first.
Is there a patch for CVE-2026-57495?
Yes. A fix has been recorded for CVE-2026-57495. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-57495 affect?
CVE-2026-57495 affects @agenticmail/claudecode < 0.2.39, @agenticmail/codex < 0.1.33, @agenticmail/core < 0.9.43, @agenticmail/openclaw < 0.5.71. Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-57495?
Upgrade to fixed versions and audit inbound-email handlers and operator-email checks.
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
External email can resume a fully-privileged agent with permissionMode:bypass, enabling command execution, webfetch, file edits, and data exfiltration using operator OAuth.
Immediate action required
- affected< 0.2.39
- affected< 0.1.33
- affected< 0.9.43
- affected< 0.5.71
As published in the CVE Program record. A version outside these ranges is not a statement that it is unaffected — vendors sometimes understate a range, and distribution-backported builds carry upstream numbers that do not reflect what was patched into them.