CVE-2026-33654
Remote prompt-injection via email channel enables arbitrary LLM commands and system tool use.
Is CVE-2026-33654 being exploited?
Not confirmed. CVE-2026-33654 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 0.49% probability of exploitation in the next 30 days.
How severe is CVE-2026-33654?
CVE-2026-33654 is rated High with a CVSS score of 8.9. 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-2026-33654?
Yes. A fix has been recorded for CVE-2026-33654. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2026-33654 affect?
CVE-2026-33654 affects nanobot <0.1.6. Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2026-33654?
Upgrade to 0.1.6+ immediately
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
Remote unauthenticated prompt injection lets attacker run LLM instructions and system tools via crafted email, bypassing channel isolation.
Immediate action required
- affected< 0.1.4.post6
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.