{"id":"CVE-2024-6331","published":"2024-08-04T00:00:15Z","modified":"2024-08-30T15:27:54Z","title":"Injection by Prompt Injection in stitionai/devika","vendor":"stitionai","product":"stitionai/devika","tier":"tail","description":{"text":"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`.","provenance":"source","from":"CVE.org"},"cvss":{"score":7.5,"severity":"HIGH","version":"3.1","vector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N","provenance":"source","from":"CVE.org CNA"},"epss":{"score":0.00496,"percentile":0.43499,"provenance":"source"},"cwes":[{"id":"CWE-74","name":"Improper Neutralization of Special Elements in Output Used by a Downstream Component"}],"references":[{"url":"https://huntr.com/bounties/d5ac1051-22fa-42f0-8d82-73267482e60f","tags":[]}],"priority":{"score":13.9,"factors":[{"name":"EPSS percentile","points":8.7},{"name":"CVSS severity","points":5.25}]},"vendorSlug":"stitionai","affectedVersions":[{"vendor":"stitionai","product":"stitionai/devika","versions":[">= unspecified, <= latest"]}],"ssvc":{"exploitation":"poc","automatable":"no","technicalImpact":"partial","timestamp":"2024-08-05T15:48:36.615476Z","from":"CISA ADP","provenance":"source"},"euvd":{"id":"EUVD-2024-47445","exploited":false,"provenance":"source"}}