CVE-2025-65720

نوع الضعف

An issue in Open Source GPT Researcher v3.3.7 allows attackers to execute arbitrary commands on a victim system via user interaction with a crafted HTML page.

المراجع

• https://github.com/assafelovic/gpt-researcher
• https://www.ox.security/blog/gpt-researcher-remote-code-execution
• https://www.ox.security/blog/mcp-supply-chain-advisory-rce-vulnerabilities-across-the-ai-ecosystem/