Remote code execution via unsandboxed visualization code
Published May 31, 2024 · Updated Nov 25, 2024
Code injection in Vanna 0.5.5 and earlier allows remote attackers to execute arbitrary Python code through a crafted ask-method question. The get_plotly_figure method passes LLM-generated Plotly text to Python exec after sanitization removes only fig.show(), leaving injected statements unrestricted. Exploitation requires externally controlled input to ask with visualization enabled, its default, and runs code with the backend process's privileges.
Summary
What happened
Code injection in Vanna 0.5.5 and earlier allows remote attackers to execute arbitrary Python code through a crafted ask-method question. The get_plotly_figure method passes LLM-generated Plotly text to Python exec after sanitization removes only fig.show(), leaving injected statements unrestricted. Exploitation requires externally controlled input to ask with visualization enabled, its default, and runs code with the backend process's privileges.
The record
- CVE
- CVE-2024-5565
- Published
- May 31, 2024
- Updated
- Nov 25, 2024
- Vendor
- Vanna AI
- Product
- Vanna
- Classifications
- CWE-94, T1059.006
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- May 31, 2024CVE publishedPublication date reported by the CVE source.
- Nov 25, 2024Record 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=-
- Affected versionversion=0
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
- JFrog Vanna ask prompt-injection 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