Injection by Prompt Injection in stitionai/devika
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- None
- Attack complexity
- Low
- Impact type
- —
- Confidentiality · integrity · availability
- High · None · None
- Fix status
- No fix listed
Attack profile from CVSS 3.1 · CNA. Fix status from CNA.
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`.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
Remediation
No fixed version listed by the sources yet.
Timeline
- 2026-10-02 Threatist record created from CVE-2024-6331
- 2026-10-03 Alias added: GHSA-699f-m7wm-gv75
References
More stitionai Devika vulnerabilities
- TI-2024-26916 The snapshot_path parameter in the /api/get-browser-snapshot endpoint in stitionai devika… CVSS 3.1CRITICAL 9.1
- TI-2024-05493 Path Traversal in stitionai/devika CVSS 3.0CRITICAL 9.1
- TI-2024-05156 Directory Traversal in stitionai/devika CVSS 3.0HIGH 7.5
- TI-2024-05155 Directory Traversal in stitionai/devika CVSS 3.0HIGH 7.5
- TI-2024-04953 Local File Read in stitionai/devika CVSS 3.0HIGH 7.5
- TI-2024-05397 Unprotected WebSocket in stitionai/devika CVSS 3.1HIGH 8.8
Sources
- CVE-2024-6331 · CVE Program
- CVE-2024-6331 · NVD
- FIRST EPSS
- GHSA-699f-m7wm-gv75 · GitHub Advisory Database · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences