{"id":"CVE-2026-31020","aliases":["EUVD-2026-71608","GHSA-6675-j46f-vjjw"],"status":"published","title":"In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users...","description":"In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chatbot interactions. This functionality renders user-supplied prompt data using Jinja templates without input sanitization or sandboxing. An unauthenticated attacker can inject malicious template expressions, leading to a server-side template injection (SSTI) vulnerability that can be exploited to achieve full remote code execution (RCE).","severity":{"version":"3.1","score":9.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical","assessor":"adp","from":"cve"},"epss":{"day":"2026-11-11","score":0.01038,"percentile":0.64367,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-94"],"published":"2026-09-04T00:00:00Z","modified":"2026-09-08T19:42:20Z","references":[{"url":"http://arc53.com"},{"url":"https://github.com/PhDg1410/CVE/tree/main/CVE-2026-31020"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-31020"},{"url":"https://github.com/advisories/GHSA-6675-j46f-vjjw"}],"sources":{"cve":[{"id":"CVE-2026-31020","description":"In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chatbot interactions. This functionality renders user-supplied prompt data using Jinja templates without input sanitization or sandboxing. An unauthenticated attacker can inject malicious template expressions, leading to a server-side template injection (SSTI) vulnerability that can be exploited to achieve full remote code execution (RCE).","status":"published","published":"2026-09-04T00:00:00Z","modified":"2026-09-04T17:39:17.358Z","cvss":[{"version":"3.1","score":9.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical","assessor":"adp"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T14:19:50.92611Z"}],"euvd":[{"id":"EUVD-2026-71608","description":"In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chatbot interactions. This functionality renders user-supplied prompt data using Jinja templates without input sanitization or sandboxing. An unauthenticated attacker can inject malicious template expressions, leading to a server-side template injection (SSTI) vulnerability that can be exploited to achieve full remote code execution (RCE).","status":"published","published":"2026-09-04T00:00:00Z","modified":"2026-09-04T17:39:17Z","cvss":[{"version":"3.1","score":9.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical"}],"updated_at":"2026-11-02T18:01:11.774269Z"}],"ghsa":[{"id":"GHSA-6675-j46f-vjjw","title":"In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users...","description":"In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chatbot interactions. This functionality renders user-supplied prompt data using Jinja templates without input sanitization or sandboxing. An unauthenticated attacker can inject malicious template expressions, leading to a server-side template injection (SSTI) vulnerability that can be exploited to achieve full remote code execution (RCE).","status":"published","published":"2026-09-04T18:31:31Z","modified":"2026-09-04T18:31:33Z","cvss":[{"version":"3.1","score":9.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T15:11:23.167848Z"}],"nvd":[{"id":"CVE-2026-31020","description":"In DocsGPT 0.15.0 and below, the application provides a custom prompt feature that allows users to define prompt content used during chatbot interactions. This functionality renders user-supplied prompt data using Jinja templates without input sanitization or sandboxing. An unauthenticated attacker can inject malicious template expressions, leading to a server-side template injection (SSTI) vulnerability that can be exploited to achieve full remote code execution (RCE).","status":"published","published":"2026-09-04T17:16:56.91Z","modified":"2026-09-08T19:42:20.313Z","cvss":[{"version":"3.1","score":9.8,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H","level":"critical","assessor":"secondary"}],"cwes":["CWE-94"],"updated_at":"2026-11-02T14:12:44.082631Z"}]}}