Authenticated code execution via LLM-generated Plotly code
Published Mar 21, 2026 · Updated Mar 21, 2026
Code injection in Vanna 2.0.0 through 2.0.2 allows remote authenticated users to execute commands through crafted chat prompts. The legacy visualization path asks the LLM for Plotly Python code and passes its output to exec() in the host process without constraining injected statements. The path requires visualization to be enabled and prompt-submission access; successful injection runs with the server process's privileges.
Summary
What happened
Code injection in Vanna 2.0.0 through 2.0.2 allows remote authenticated users to execute commands through crafted chat prompts. The legacy visualization path asks the LLM for Plotly Python code and passes its output to exec() in the host process without constraining injected statements. The path requires visualization to be enabled and prompt-submission access; successful injection runs with the server process's privileges.
The record
- CVE
- CVE-2026-4511
- Published
- Mar 21, 2026
- Updated
- Mar 21, 2026
- Vendor
- Vanna AI
- Product
- Vanna
- Classifications
- CWE-707, CWE-74, T1059.006
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Mar 21, 2026CVE publishedPublication date reported by the CVE source.
- Mar 21, 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=2.0.0
- Affected versionversion=2.0.1
- Affected versionversion=2.0.2
What conditions does exploitation require?
What is affected?
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
- Prompt injection to RCE proof of conceptproof of concept · unverified
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