Remote tool execution via spoofed email sender
Published Mar 27, 2026 · Updated Mar 27, 2026
Indirect prompt injection in nanobot before 0.1.4.post6 allows remote attackers to execute agent tools through a spoofed email. The email channel's _fetch_messages method trusts the forgeable RFC 5322 From header as sender_id, passes the body to AgentLoop, and authorizes it against allow_from without SPF, DKIM, or DMARC verification. Exploitation requires the email channel and a forged allowlisted sender; enabled ExecTool access permits system command execution without owner interaction.
Summary
What happened
Indirect prompt injection in nanobot before 0.1.4.post6 allows remote attackers to execute agent tools through a spoofed email. The email channel's _fetch_messages method trusts the forgeable RFC 5322 From header as sender_id, passes the body to AgentLoop, and authorizes it against allow_from without SPF, DKIM, or DMARC verification. Exploitation requires the email channel and a forged allowlisted sender; enabled ExecTool access permits system command execution without owner interaction.
The record
- CVE
- CVE-2026-33654
- Published
- Mar 27, 2026
- Updated
- Mar 27, 2026
- Vendor
- Data Intelligence Lab @ HKU
- Product
- nanobot
- Classifications
- CWE-1336, CWE-94, CWE-290
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 27, 2026CVE publishedPublication date reported by the CVE source.
- Mar 27, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 0.1.4.post6
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- GHSA email-sender spoofing proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo