CrewAI Vulnerabilities Expose Devices to Hacking Researchers found four chained vulnerabilities in the open-source Python multi-agent framework CrewAI that can be exploited—via the Code Interpreter and its SandboxPython fallback—to escape sandboxes, execute arbitrary code, perform SSRF, and read local files. CrewAI maintainers are working on mitigations including blocking risky modules, changing defaults to fail closed, clearer runtime...

Four chained vulnerabilities in CrewAI’s Python multi-agent framework allow sandbox escape, arbitrary code execution, SSRF, and local file access. Fixes include blocking risky modules and stricter defaults. #CrewAI #CodeInterp #CVE2026