CVE-2026-33654

Zero-Click Indirect Prompt Injection and Authentication Bypass via Email Polling

Published Mar 27, 2026 CVSS 4.0 · 8.9 High EPSS < 1% KEV · Not listed
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.

Analysis

AI-generated

Technical impact

An indirect prompt injection flaw in nanobot's email channel allows a remote, unauthenticated attacker to deliver malicious content through a monitored email address, where the bot treats the email body as fully trusted input, injects it into the large language model for instruction generation, and can trigger system tools; the attacker can thus execute arbitrary LLM instructions and effectively run code on the host, leading to full system compromise.

Affected Systems

The vulnerability affects the nanobot personal AI assistant developed by HKUDS in any release prior to version 0.1.6, including 0.1.4 and its post versions (post1 through post5), as well as any earlier releases that contain the same email channel code; the software runs in Python environments.

Risk and Exploitability

The CVSS score of 8.9 classifies this vulnerability as high severity, and the EPSS score of less than 1 % indicates a low likelihood of exploitation in the wild; nevertheless, the attack requires only a single, zero‑click email with no user interaction, and since the flaw is not listed in the CISA KEV catalog there is no evidence of widespread exploitation yet, but administrators should treat it as a high‑risk issue that can be triggered remotely via email.

Remediation

No solution or workaround provided in the CVE record.

OpenCVE Recommended Actions

  • Upgrade nanobot to version 0.1.6 or later.
  • Disable or temporarily block the email channel until the patch is applied if upgrading immediately is not possible.
  • Review and monitor email logs for anomalous activity to detect potential exploitation attempts.

Generated by OpenCVE AI on April 8, 2026 at 16:28 UTC.

Tracking

Sign in to view the affected projects.

Advisories

No advisories available
History
Type Values Removed Values Added
First Time appeared Nanobot
Nanobot nanobot
CPEs cpe:2.3:a:nanobot:nanobot:*:*:*:*:*:python:*:*
cpe:2.3:a:nanobot:nanobot:0.1.4:-:*:*:*:python:*:*
cpe:2.3:a:nanobot:nanobot:0.1.4:post1:*:*:*:python:*:*
cpe:2.3:a:nanobot:nanobot:0.1.4:post2:*:*:*:python:*:*
cpe:2.3:a:nanobot:nanobot:0.1.4:post3:*:*:*:python:*:*
cpe:2.3:a:nanobot:nanobot:0.1.4:post4:*:*:*:python:*:*
cpe:2.3:a:nanobot:nanobot:0.1.4:post5:*:*:*:python:*:*
Vendors & Products Nanobot
Nanobot nanobot
Metrics cvssV3_1

{'score': 9.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'}

Type Values Removed Values Added
Metrics ssvc

{'options': {'Automatable': 'yes', 'Exploitation': 'poc', 'Technical Impact': 'total'}, 'version': '2.0.3'}

Type Values Removed Values Added
First Time appeared Hkuds
Hkuds nanobot
Vendors & Products Hkuds
Hkuds nanobot
Type Values Removed Values Added
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.
Title Zero-Click Indirect Prompt Injection and Authentication Bypass via Email Polling
Weaknesses CWE-1336
CWE-290
CWE-94
References
Metrics cvssV4_0

{'score': 8.9, 'vector': 'CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:P'}

Weaknesses
  • CWE-1336

    Improper Neutralization of Special Elements Used in a Template Engine

  • CWE-290

    Authentication Bypass by Spoofing

  • CWE-94

    Improper Control of Generation of Code ('Code Injection')

Sources

Status
PUBLISHED
Assigner
GitHub_M
Published
Updated
Mar 30, 2026, 6:59 PM
Reserved
Mar 23, 2026, 3:23 PM
Status
Analyzed
Published
Mar 27, 2026, 8:16 PM
Modified
Oct 26, 2026, 9:10 PM