CVE-2026-33654: CWE-94: Improper Control of Generation of Code ('Code Injection') in HKUDS nanobot
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.
AI Analysis
Technical Summary
The vulnerability exists in the nanobot email channel processing module (nanobot/channels/email.py) before version 0.1.6. An attacker can send malicious prompts via email to the bot's monitored address, which the bot automatically polls and processes without user interaction. This leads to arbitrary code execution through the LLM and underlying system tools, exploiting improper control of code generation (CWE-94). The vulnerability has a CVSS 4.0 score of 8.9, indicating high severity. The flaw is fixed in nanobot version 0.1.6.
Potential Impact
An unauthenticated remote attacker can execute arbitrary instructions and system commands on the affected system by sending specially crafted emails. This can lead to full compromise of the AI assistant environment without any user interaction, due to the bot treating email content as trusted input and bypassing channel isolation controls.
Mitigation Recommendations
Upgrade nanobot to version 0.1.6 or later, where this vulnerability is patched. No other mitigations are indicated or required as the fix addresses the root cause.
CVE-2026-33654: CWE-94: Improper Control of Generation of Code ('Code Injection') in HKUDS nanobot
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.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
The vulnerability exists in the nanobot email channel processing module (nanobot/channels/email.py) before version 0.1.6. An attacker can send malicious prompts via email to the bot's monitored address, which the bot automatically polls and processes without user interaction. This leads to arbitrary code execution through the LLM and underlying system tools, exploiting improper control of code generation (CWE-94). The vulnerability has a CVSS 4.0 score of 8.9, indicating high severity. The flaw is fixed in nanobot version 0.1.6.
Potential Impact
An unauthenticated remote attacker can execute arbitrary instructions and system commands on the affected system by sending specially crafted emails. This can lead to full compromise of the AI assistant environment without any user interaction, due to the bot treating email content as trusted input and bypassing channel isolation controls.
Mitigation Recommendations
Upgrade nanobot to version 0.1.6 or later, where this vulnerability is patched. No other mitigations are indicated or required as the fix addresses the root cause.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-03-23T15:23:42.218Z
- Cvss Version
- 4.0
- State
- PUBLISHED
Threat ID: 69c6e1b93c064ed76febd414
Added to database: 3/27/2026, 7:59:53 PM
Last enriched: 4/4/2026, 10:58:43 AM
Last updated: 5/12/2026, 3:34:47 AM
Views: 89
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.