{"vulnerability": "cve-2024-6331", "sightings": [{"uuid": "9946f0c8-a0b1-4b2b-acf0-a995563ff186", "vulnerability_lookup_origin": "1a89b78e-f703-45f3-bb86-59eb712668bd", "author": "9f56dd64-161d-43a6-b9c3-555944290a09", "vulnerability": "CVE-2024-6331", "type": "seen", "source": "https://t.me/cvedetector/2405", "content": "{\n  \"Source\": \"CVE FEED\",\n  \"Title\": \"CVE-2024-6331 - Devika Google Gimini Local File Read (LFI) via Prompt Injection\", \n  \"Content\": \"CVE ID : CVE-2024-6331 \nPublished : Aug. 4, 2024, 12:15 a.m. | 28\u00a0minutes ago \nDescription : 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`. \nSeverity: 7.5 | HIGH \nVisit the link for more details, such as CVSS details, affected products, timeline, and more...\",\n  \"Detection Date\": \"04 Aug 2024\",\n  \"Type\": \"Vulnerability\"\n}\n\ud83d\udd39 t.me/cvedetector \ud83d\udd39", "creation_timestamp": "2024-08-04T02:47:52.000000Z"}]}