CVE-2026-33654 Zero-Click Indirect Prompt Injection and Authentication Bypass via Email Polling
Remote attackers can execute arbitrary code via prompt injection in email processing, bypassing authentication without user interaction.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- None listed
What is CVE-2026-33654?
CVE-2026-33654 is a high-severity code injection vulnerability in HKUDS nanobot, published on 27 Mar 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
nanobot is a personal AI assistant. Prior to version 0.1.6, an indirect prompt injection vulnerability exists in the email channel processing module (`nanobot/channels/email.py`), allowing a remote, unauthenticated attacker to execute arbitrary LLM instructions (and subsequently, system tools) without any interaction from the bot owner. By sending an email containing malicious prompts to the bot's monitored email address, the bot automatically polls, ingests, and processes the email content as highly trusted input, fully bypassing channel isolation and resulting in a stealthy, zero-click attack. Version 0.1.6 patches the issue.
Which versions are affected by CVE-2026-33654?
It affects 1 product.
Products include Nanobot Nanobot.
How do I fix CVE-2026-33654?
No fix has been published for CVE-2026-33654 yet. Limit exposure of the affected software until one is available.
Upgrade, and never evaluate templates, expressions or code built from user input. More about Code injection.
Is CVE-2026-33654 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-33654 exists.
Other vulnerabilities in HKUDS nanobot
Sources
Also known as GHSA-4gmr-2vc8-7qh3.