LLMHigh
CVE-2024-6331: stitionai/devika main branch as of commit cdfb782b0e634b773b10963c8034dc9207ba1f9f is vulnerable to …
- Occurred
- Aug 4, 2024
- Published
- Aug 4, 2024
- Source
- NVD CVE
Summary
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`.
Tags
- CVE
- CVE-2024-6331
- cvss:HIGH
Classification
Category confidence: 90%
Severity confidence: 85%
Rationale: LLM vulnerability enables local file read via prompt injection, allowing sensitive data access.
Classifier: Qwen/Qwen3.5-35B-A3B-FP8