CVE-2025-12695 Details
Description
The overly permissive sandbox configuration in DSPy allows attackers to steal sensitive files in cases when users build an AI agent which consumes user input and uses the “PythonInterpreter” class.
A vulnerability in JFrog DSPy has been identified, stemming from an overly permissive sandbox configuration. This flaw allows attackers to read sensitive files when users create AI agents that process input and utilize the 'PythonInterpreter' class. The issue arises from the insecure handling of untrusted code within the sandbox environment.
Metrics
CVSS 4.0 Severity and Vector Strings:
CVSS 3.x Severity and Vector Strings:
No data available for CVSS Version 2.0 on this CVE.
Volerion
Assessed Nov 4, 2025CISA-ADP
Assessed Nov 4, 2025References to Advisories, Solutions, and Tools
By selecting these links, you will be leaving this site. These are references gathered from the official CVE record and are not endorsed by Volerion.
| URL | Source(s) | Tag(s) |
|---|---|---|
| https://research.jfrog.com/vulnerabilities/dspy-sandbox-escape-arbitrary-file-read-jfsa-2025-001495652/ | [email protected] | AdvisoryExploitRemedy |
Weakness Enumeration
| CWE-ID | CWE Name | Source |
|---|---|---|
| CWE-653 | Improper Isolation or Compartmentalization | [email protected] |
Affected Products
| Product | Versions |
|---|---|
| JFrog DSPy | All versions |
CPE
Remediation
| |
Change History
4 change records found show changes
| Date | Action | Recorded By |
|---|---|---|
| Nov 5, 2026 | CVE Translated | [email protected] |
| Jun 17, 2026 | CVE Modified | [email protected] |
| Jun 17, 2026 | CVE Modified | CISA-ADP |
| Nov 4, 2025 | New CVE Received | [email protected] |
Volerion