DSPy does not properly restrict file reads
CVE-2025-12695 · GHSA-vvw2-h478-xwr3 · published 2025-11-04
- Severity
- Medium
- CVSS score
- 5.9
- Chance of exploitation (EPSS)
- 0.34%
- Fixed in
- No fix yet
- Exploitation Public proof of concept
- Automatable Yes
- Technical impact Partial
- CISA SSVC
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.
No fixed release is listed yet for dspy. Limit what it can reach, or stop using it until a fix ships, and follow the source advisory for updates.
| Package | Registry | Affected | Fixed in |
|---|---|---|---|
| dspy | PyPI | <= 3.0.3 | No fix yet |
- CriticalLiteLLM has SQL Injection in Proxy API key verificationlitellmExploited
- Criticaln8n Vulnerable to Remote Code Execution via Expression Injectionn8n, n8nExploited
- HighLiteLLM has a sandbox escape in custom-code guardraillitellmExploited
- HighLangflow affected by Remote Code Execution via validate_code() exec()langflowExploited
- CriticalJupyter MCP Server: Browser DNS rebinding can hijack the Jupyter backend through management routesjupyter-mcp-server
- Criticalmem0ai Databricks vector store vulnerable to SQL injectionmem0ai
The impact, patch and workaround text comes from the advisory, shortened (GitHub Advisory Database, CC BY 4.0). Proof-of-concept and reproduction sections and code are left out; the original advisory has them.