{"id":"CVE-2024-6331","aliases":["EUVD-2024-47445","GHSA-699f-m7wm-gv75"],"status":"published","title":"Injection by Prompt Injection in stitionai/devika","description":"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`.","severity":{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-07","score":0.00496,"percentile":0.42835,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":false},"cwes":["CWE-200","CWE-74"],"published":"2024-08-04T00:00:15Z","modified":"2026-06-17T08:17:47Z","products":[{"vendor":"stitionai","product":"devika"},{"vendor":"stitionai","product":"stitionai/devika"}],"references":[{"url":"https://huntr.com/bounties/d5ac1051-22fa-42f0-8d82-73267482e60f","tags":["Exploit","Third Party Advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2024-6331"},{"url":"https://github.com/advisories/GHSA-699f-m7wm-gv75"}],"sources":{"cve":[{"id":"CVE-2024-6331","title":"Injection by Prompt Injection in stitionai/devika","description":"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`.","status":"published","published":"2024-08-04T00:00:15.148Z","modified":"2024-08-30T15:27:54.554Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","level":"high","assessor":"cna"}],"cwes":["CWE-74"],"updated_at":"2026-11-02T14:34:10.961618Z"}],"euvd":[{"id":"EUVD-2024-47445","description":"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`.","status":"published","published":"2024-08-04T00:00:15Z","modified":"2024-08-30T15:27:54Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","level":"high"}],"updated_at":"2026-11-03T00:56:07.010485Z"}],"ghsa":[{"id":"GHSA-699f-m7wm-gv75","title":"stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable...","description":"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`.","status":"published","published":"2024-08-04T00:30:35Z","modified":"2024-08-20T21:31:32Z","cvss":[{"version":"3.0","score":7.5,"vector":"CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","level":"high"}],"cwes":["CWE-74","CWE-200"],"updated_at":"2026-11-02T14:58:01.859506Z"}],"nvd":[{"id":"CVE-2024-6331","description":"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`.","status":"published","published":"2024-08-04T00:15:47.863Z","modified":"2026-06-17T08:17:47.68Z","cvss":[{"version":"3.1","score":7.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","level":"high","assessor":"secondary"},{"version":"3.1","score":6.5,"vector":"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N","level":"medium","assessor":"primary"}],"cwes":["CWE-74"],"updated_at":"2026-11-02T14:10:17.832118Z"}]}}