Skip to content
AI AgentHigh

CVE-2026-33654: nanobot is a personal AI assistant. Prior to version 0.1.6, an indirect prompt injection vulnerabili…

Occurred
Mar 27, 2026
Published
Mar 27, 2026
Source
NVD CVE

Summary

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.

Tags

  • CVE
  • CVE-2026-33654
  • cvss:CRITICAL
  • agent-fail:injection-indirect
  • agent-cause:missing-guardrail

Classification

Category confidence: 95%
Severity confidence: 90%

Rationale: CVE describes indirect prompt injection vulnerability in AI assistant allowing unauthorized tool execution via email.

Classifier: Qwen/Qwen3.5-35B-A3B-FP8

Visit source