CVE-2026-33654 Zero-Click Indirect Prompt Injection and Authentication Bypass via Email Polling
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- Proof of concept public · automatable: yes · technical impact: total
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.
Upgrade path
2 packages: 1 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| nanobot | < 0.1.4; = 0.1.4; = 0.1.4-post1; = 0.1.4-post2 +3 more | 0.1.4 | Fixed |
| HKUDS nanobot | = < 0.1.4.post6 | No fix listed | Versions listed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| HKUDS nanobot | = < 0.1.4.post6 | No fix listed |
| nanobot | < 0.1.4 | 0.1.4 |
| nanobot | = 0.1.4 | No fix listed |
| nanobot | = 0.1.4-post1 | No fix listed |
| nanobot | = 0.1.4-post2 | No fix listed |
| nanobot | = 0.1.4-post3 | No fix listed |
| nanobot | = 0.1.4-post4 | No fix listed |
| nanobot | = 0.1.4-post5 | No fix listed |
References
- https://github.com/HKUDS/nanobot/security/advisories/GHSA-4gmr-2vc8-7qh3 exploit mitigation vendor-advisory