stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to Local File Read (LFI) by Prompt Injection. The integration of Google Gimini 1.0 Pro with `HarmBlockThreshold.BLOCK_NONE` for `HarmCategory.HARM_CATEGORY_HATE_SPEECH` and `HarmCategory.HARM_CATEGORY_HARASSMENT` in `safety_settings` disables content protection. This allows malicious commands to be executed, such as reading sensitive file contents like `/etc/passwd`.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:NStitionai Devika
APPStitionai≥ 2024-05-02
Related vulnerabilities
Path traversal w Stitionai Devika v1 — nieautoryzowany dostęp do plików
Path traversal w Stitionai Devika — odczyt plików i DoS
A CORS misconfiguration in the stitionai/devika repository allows attackers to steal sensitive information suc...
A Cross-Site Request Forgery (CSRF) vulnerability was identified in the stitionai/devika application, affectin...
A directory traversal vulnerability exists in the stitionai/devika repository, specifically within the /api/do...