How exploitable is this vulnerability in practice?

The issue is highly exploitable because it only requires the ability to send an email to the bot's monitored address. No authentication or user interaction is needed, and the attack can be carried out remotely, making it suitable for broad, opportunistic exploitation.

Does an attacker need access to the Nanobot host or email account?

No. The attacker simply needs to deliver email to the monitored inbox. The vulnerability stems from how the email channel processes message content, not from any compromise of the host or email credentials.

What is the safest general fix pattern for developers integrating external channels with AI agents?

Treat all channel content as untrusted user input; ensure it is clearly separated from system and developer instructions; apply strict instruction hierarchies; and introduce policy layers between LLM output and any tools or system actions. In short, re-establish the data-versus-control boundary and apply least privilege to what the model can cause the system to do.

Severity:

CRITICAL RISK

(9.8)

Indirect Prompt Injection (CWE-94) via Email Channel in Nanobot Personal AI Assistant

CVE-2026-33654

Published:

Mar 27, 2026

Status:

Analyzed

Summary

Affected Context

Exploit Preconditions

Why This Happens

Potential Impact

General Mitigation Guidance

How Teams Detect Issues Like This

Frequently Asked Questions

Source

NDV

Recent Vulnerabilities

CWE-77;CWE-78

CRITICAL RISK

CRITICAL

(9.8)

OS Command Injection (CWE-78) in Totolink A7100RU CGI Handler setAccessDeviceCfg

Remote Code Execution on the Router

April 12, 2026

CWE-77;CWE-78

CRITICAL RISK

CRITICAL

(9.8)

OS Command Injection (CWE-78) in Totolink A7100RU CGI setLedCfg Handler

Remote Code Execution on the Router

April 12, 2026

Vulnerability Type

Category:

Prompt Injection / AI Instruction Manipulation

CWE:

CWE-94;CWE-290;CWE-1336

Impact:

Remote, unauthenticated arbitrary LLM instruction execution with potential tool/system action compromise

Severity:

CRITICAL RISK

(9.8)

CVSS Version:

3.1

Vulnerability Type

Category:

Prompt Injection / AI Instruction Manipulation

CWE:

CWE-94;CWE-290;CWE-1336

Impact:

Remote, unauthenticated arbitrary LLM instruction execution with potential tool/system action compromise

Severity:

CRITICAL RISK

(9.8)

CVSS Version:

3.1

Catch This CVE While Code Is Being Written

Detect vulnerable code directly in pull requests, so CVEs are fixed before merge.

Get Started

Ship clean & secure code faster

START 14 DAYS FREE TRIAL

BOOK A DEMO

Made with Love in San Francisco

355 Bryant St. San Francisco, CA 94107, USA

Ask AI for summary of CodeAnt

Made with Love in San Francisco

355 Bryant St. San Francisco, CA 94107, USA

Ask AI for summary of CodeAnt

Made with Love in San Francisco

355 Bryant St. San Francisco, CA 94107, USA

Ask AI for summary of CodeAnt

Indirect Prompt Injection (CWE-94) via Email Channel in Nanobot Personal AI Assistant

Summary

Affected Context

Exploit Preconditions

Why This Happens

Potential Impact

General Mitigation Guidance

How Teams Detect Issues Like This

Frequently Asked Questions

Source

Recent Vulnerabilities

CRITICAL RISK

CRITICAL

(9.8)

OS Command Injection (CWE-78) in Totolink A7100RU CGI Handler setAccessDeviceCfg

CRITICAL RISK

CRITICAL

(9.8)

OS Command Injection (CWE-78) in Totolink A7100RU CGI setLedCfg Handler

Vulnerability Type

Vulnerability Type

Vulnerability Type

Catch This CVE While Code Is Being Written

Ship clean & secure code faster

Product

Pricing

Company

Legal

Developers

Compare

Product

Pricing

Company

Legal

Developers

Compare

Product

Pricing

Company

Legal

Developers

Compare